From 012b88d7a2d80de99b2b580a3a67b052799cfccc Mon Sep 17 00:00:00 2001
From: Svetlana Karslioglu <svekars@meta.com>
Date: Mon, 10 Nov 2025 12:27:54 -0800
Subject: [PATCH] Fix links to sources for 2.9.0

---
 2.9/amp.html                                  |  20 +-
 2.9/autograd.html                             |  26 +-
 2.9/backends.html                             |  76 +--
 2.9/benchmark_utils.html                      |  44 +-
 2.9/checkpoint.html                           |  12 +-
 2.9/cond.html                                 |   2 +-
 2.9/config_mod.html                           |   4 +-
 2.9/cpp_extension.html                        |  20 +-
 2.9/cuda._sanitizer.html                      |   2 +-
 2.9/cuda.html                                 |   2 +-
 2.9/cuda.tunable.html                         |  42 +-
 2.9/data.html                                 |  40 +-
 2.9/ddp_comm_hooks.html                       |  24 +-
 2.9/distributed._dist2.html                   |  10 +-
 2.9/distributed.algorithms.join.html          |  14 +-
 2.9/distributed.checkpoint.html               | 176 +++---
 2.9/distributed.fsdp.fully_shard.html         |  42 +-
 2.9/distributed.html                          | 104 ++--
 2.9/distributed.optim.html                    |  26 +-
 2.9/distributed.pipelining.html               |  40 +-
 2.9/distributed.tensor.html                   |  62 +--
 2.9/distributed.tensor.parallel.html          |  16 +-
 2.9/distributions.html                        | 518 +++++++++---------
 2.9/dlpack.html                               |   2 +-
 2.9/elastic/agent.html                        |  50 +-
 2.9/elastic/control_plane.html                |   2 +-
 2.9/elastic/errors.html                       |   8 +-
 2.9/elastic/events.html                       |  10 +-
 2.9/elastic/metrics.html                      |  12 +-
 2.9/elastic/multiprocessing.html              |  20 +-
 2.9/elastic/numa.html                         |   6 +-
 2.9/elastic/rendezvous.html                   |  90 +--
 2.9/elastic/subprocess_handler.html           |   4 +-
 2.9/elastic/timer.html                        |  30 +-
 2.9/export/api_reference.html                 | 136 ++---
 2.9/export/joint_with_descriptors.html        |  86 +--
 2.9/fsdp.html                                 |  70 +--
 2.9/future_mod.html                           |   8 +-
 2.9/futures.html                              |  18 +-
 2.9/fx.html                                   | 162 +++---
 2.9/generated/torch.Tensor.backward.html      |   2 +-
 2.9/generated/torch.Tensor.dim_order.html     |   2 +-
 2.9/generated/torch.Tensor.is_shared.html     |   2 +-
 2.9/generated/torch.Tensor.istft.html         |   2 +-
 2.9/generated/torch.Tensor.lu.html            |   2 +-
 2.9/generated/torch.Tensor.module_load.html   |   2 +-
 2.9/generated/torch.Tensor.norm.html          |   2 +-
 2.9/generated/torch.Tensor.register_hook.html |   2 +-
 ...or.register_post_accumulate_grad_hook.html |   2 +-
 2.9/generated/torch.Tensor.share_memory_.html |   2 +-
 2.9/generated/torch.Tensor.split.html         |   2 +-
 2.9/generated/torch.Tensor.stft.html          |   2 +-
 2.9/generated/torch.Tensor.storage.html       |   2 +-
 2.9/generated/torch.Tensor.storage_type.html  |   2 +-
 2.9/generated/torch.Tensor.to_sparse_coo.html |   2 +-
 2.9/generated/torch.Tensor.unflatten.html     |   2 +-
 2.9/generated/torch.Tensor.unique.html        |   2 +-
 .../torch.Tensor.unique_consecutive.html      |   2 +-
 2.9/generated/torch._assert.html              |   2 +-
 2.9/generated/torch._logging.set_logs.html    |   2 +-
 ...torch.accelerator.current_accelerator.html |   2 +-
 .../torch.accelerator.current_device_idx.html |   2 +-
 ...orch.accelerator.current_device_index.html |   2 +-
 .../torch.accelerator.current_stream.html     |   2 +-
 .../torch.accelerator.device_count.html       |   2 +-
 .../torch.accelerator.device_index.html       |   2 +-
 .../torch.accelerator.is_available.html       |   2 +-
 .../torch.accelerator.memory.empty_cache.html |   2 +-
 ...celerator.memory.max_memory_allocated.html |   2 +-
 ...ccelerator.memory.max_memory_reserved.html |   2 +-
 ...h.accelerator.memory.memory_allocated.html |   2 +-
 ...ch.accelerator.memory.memory_reserved.html |   2 +-
 ...torch.accelerator.memory.memory_stats.html |   2 +-
 ...memory.reset_accumulated_memory_stats.html |   2 +-
 ...erator.memory.reset_peak_memory_stats.html |   2 +-
 .../torch.accelerator.set_device_idx.html     |   2 +-
 .../torch.accelerator.set_device_index.html   |   2 +-
 .../torch.accelerator.set_stream.html         |   2 +-
 .../torch.accelerator.synchronize.html        |   2 +-
 .../torch.ao.nn.intrinsic.BNReLU2d.html       |   2 +-
 .../torch.ao.nn.intrinsic.BNReLU3d.html       |   2 +-
 .../torch.ao.nn.intrinsic.ConvBn1d.html       |   2 +-
 .../torch.ao.nn.intrinsic.ConvBn2d.html       |   2 +-
 .../torch.ao.nn.intrinsic.ConvBn3d.html       |   2 +-
 .../torch.ao.nn.intrinsic.ConvBnReLU1d.html   |   2 +-
 .../torch.ao.nn.intrinsic.ConvBnReLU2d.html   |   2 +-
 .../torch.ao.nn.intrinsic.ConvBnReLU3d.html   |   2 +-
 .../torch.ao.nn.intrinsic.ConvReLU1d.html     |   2 +-
 .../torch.ao.nn.intrinsic.ConvReLU2d.html     |   2 +-
 .../torch.ao.nn.intrinsic.ConvReLU3d.html     |   2 +-
 .../torch.ao.nn.intrinsic.LinearReLU.html     |   2 +-
 .../torch.ao.nn.intrinsic.qat.ConvBn1d.html   |   2 +-
 .../torch.ao.nn.intrinsic.qat.ConvBn2d.html   |   2 +-
 .../torch.ao.nn.intrinsic.qat.ConvBn3d.html   |   2 +-
 ...orch.ao.nn.intrinsic.qat.ConvBnReLU1d.html |   2 +-
 ...orch.ao.nn.intrinsic.qat.ConvBnReLU2d.html |   2 +-
 ...orch.ao.nn.intrinsic.qat.ConvBnReLU3d.html |   2 +-
 .../torch.ao.nn.intrinsic.qat.ConvReLU2d.html |   2 +-
 .../torch.ao.nn.intrinsic.qat.ConvReLU3d.html |   2 +-
 .../torch.ao.nn.intrinsic.qat.LinearReLU.html |   2 +-
 ...h.ao.nn.intrinsic.qat.freeze_bn_stats.html |   2 +-
 ...h.ao.nn.intrinsic.qat.update_bn_stats.html |   2 +-
 ...ch.ao.nn.intrinsic.quantized.BNReLU2d.html |   2 +-
 ...ch.ao.nn.intrinsic.quantized.BNReLU3d.html |   2 +-
 ....ao.nn.intrinsic.quantized.ConvReLU1d.html |   2 +-
 ....ao.nn.intrinsic.quantized.ConvReLU2d.html |   2 +-
 ....ao.nn.intrinsic.quantized.ConvReLU3d.html |   2 +-
 ....ao.nn.intrinsic.quantized.LinearReLU.html |   2 +-
 ...ntrinsic.quantized.dynamic.LinearReLU.html |   2 +-
 2.9/generated/torch.ao.nn.qat.Conv2d.html     |   2 +-
 2.9/generated/torch.ao.nn.qat.Conv3d.html     |   2 +-
 2.9/generated/torch.ao.nn.qat.Linear.html     |   4 +-
 .../torch.ao.nn.qat.dynamic.Linear.html       |   2 +-
 .../torch.ao.nn.quantizable.LSTM.html         |   2 +-
 ....ao.nn.quantizable.MultiheadAttention.html |   6 +-
 .../torch.ao.nn.quantized.BatchNorm2d.html    |   2 +-
 .../torch.ao.nn.quantized.BatchNorm3d.html    |   2 +-
 .../torch.ao.nn.quantized.Conv1d.html         |   4 +-
 .../torch.ao.nn.quantized.Conv2d.html         |   4 +-
 .../torch.ao.nn.quantized.Conv3d.html         |   4 +-
 ...torch.ao.nn.quantized.ConvTranspose1d.html |   2 +-
 ...torch.ao.nn.quantized.ConvTranspose2d.html |   2 +-
 ...torch.ao.nn.quantized.ConvTranspose3d.html |   2 +-
 2.9/generated/torch.ao.nn.quantized.ELU.html  |   2 +-
 .../torch.ao.nn.quantized.Embedding.html      |   4 +-
 .../torch.ao.nn.quantized.EmbeddingBag.html   |   4 +-
 ...rch.ao.nn.quantized.FXFloatFunctional.html |   2 +-
 ...torch.ao.nn.quantized.FloatFunctional.html |   2 +-
 .../torch.ao.nn.quantized.GroupNorm.html      |   2 +-
 .../torch.ao.nn.quantized.Hardswish.html      |   2 +-
 .../torch.ao.nn.quantized.InstanceNorm1d.html |   2 +-
 .../torch.ao.nn.quantized.InstanceNorm2d.html |   2 +-
 .../torch.ao.nn.quantized.InstanceNorm3d.html |   2 +-
 .../torch.ao.nn.quantized.LayerNorm.html      |   2 +-
 .../torch.ao.nn.quantized.LeakyReLU.html      |   2 +-
 .../torch.ao.nn.quantized.Linear.html         |   6 +-
 .../torch.ao.nn.quantized.QFunctional.html    |   2 +-
 .../torch.ao.nn.quantized.ReLU6.html          |   2 +-
 .../torch.ao.nn.quantized.Sigmoid.html        |   2 +-
 .../torch.ao.nn.quantized.dynamic.GRU.html    |   2 +-
 ...torch.ao.nn.quantized.dynamic.GRUCell.html |   2 +-
 .../torch.ao.nn.quantized.dynamic.LSTM.html   |   2 +-
 ...orch.ao.nn.quantized.dynamic.LSTMCell.html |   2 +-
 .../torch.ao.nn.quantized.dynamic.Linear.html |   6 +-
 ...torch.ao.nn.quantized.dynamic.RNNCell.html |   2 +-
 ...ntized.functional.adaptive_avg_pool2d.html |   2 +-
 ...ntized.functional.adaptive_avg_pool3d.html |   2 +-
 ...ao.nn.quantized.functional.avg_pool2d.html |   2 +-
 ...ao.nn.quantized.functional.avg_pool3d.html |   2 +-
 ...torch.ao.nn.quantized.functional.celu.html |   2 +-
 ...orch.ao.nn.quantized.functional.clamp.html |   2 +-
 ...rch.ao.nn.quantized.functional.conv1d.html |   2 +-
 ...rch.ao.nn.quantized.functional.conv2d.html |   2 +-
 ...rch.ao.nn.quantized.functional.conv3d.html |   2 +-
 .../torch.ao.nn.quantized.functional.elu.html |   2 +-
 ...o.nn.quantized.functional.hardsigmoid.html |   2 +-
 ....ao.nn.quantized.functional.hardswish.html |   2 +-
 ...h.ao.nn.quantized.functional.hardtanh.html |   2 +-
 ...o.nn.quantized.functional.interpolate.html |   2 +-
 ...ao.nn.quantized.functional.leaky_relu.html |   2 +-
 ...rch.ao.nn.quantized.functional.linear.html |   2 +-
 ...ao.nn.quantized.functional.max_pool1d.html |   2 +-
 ...ao.nn.quantized.functional.max_pool2d.html |   2 +-
 ....ao.nn.quantized.functional.threshold.html |   2 +-
 ...h.ao.nn.quantized.functional.upsample.html |   2 +-
 ...uantized.functional.upsample_bilinear.html |   2 +-
 ...quantized.functional.upsample_nearest.html |   2 +-
 .../torch.ao.quantization.DeQuantStub.html    |   2 +-
 .../torch.ao.quantization.QuantStub.html      |   2 +-
 .../torch.ao.quantization.QuantWrapper.html   |   2 +-
 ...rch.ao.quantization.add_quant_dequant.html |   2 +-
 ...tization.backend_config.BackendConfig.html |  12 +-
 ...n.backend_config.BackendPatternConfig.html |  24 +-
 ...antization.backend_config.DTypeConfig.html |   6 +-
 ...n.backend_config.DTypeWithConstraints.html |   2 +-
 ...zation.backend_config.ObservationType.html |   2 +-
 ...torch.ao.quantization.compare_results.html |   2 +-
 .../torch.ao.quantization.convert.html        |   2 +-
 ...torch.ao.quantization.default_eval_fn.html |   2 +-
 ...tization.extract_results_from_loggers.html |   2 +-
 ...antization.fake_quantize.FakeQuantize.html |   2 +-
 ...zation.fake_quantize.FakeQuantizeBase.html |   2 +-
 ...ake_quantize.FixedQParamsFakeQuantize.html |   4 +-
 ...uantize.FusedMovingAvgObsFakeQuantize.html |   2 +-
 ...tion.fake_quantize.disable_fake_quant.html |   2 +-
 ...zation.fake_quantize.disable_observer.html |   2 +-
 ...ation.fake_quantize.enable_fake_quant.html |   2 +-
 ...ization.fake_quantize.enable_observer.html |   2 +-
 ...uantization.fuse_modules.fuse_modules.html |   2 +-
 ....fx.custom_config.ConvertCustomConfig.html |  10 +-
 ...ion.fx.custom_config.FuseCustomConfig.html |   8 +-
 ....fx.custom_config.PrepareCustomConfig.html |  22 +-
 ...om_config.StandaloneModuleConfigEntry.html |   2 +-
 ...ization.generate_numeric_debug_handle.html |   2 +-
 ....observer.AffineQuantizedObserverBase.html |  10 +-
 ....ao.quantization.observer.Granularity.html |   2 +-
 ...antization.observer.HistogramObserver.html |   2 +-
 ....ao.quantization.observer.MappingType.html |   2 +-
 ....quantization.observer.MinMaxObserver.html |   8 +-
 ....observer.MovingAverageMinMaxObserver.html |   2 +-
 ...MovingAveragePerChannelMinMaxObserver.html |   2 +-
 ...ao.quantization.observer.NoopObserver.html |   2 +-
 ...ao.quantization.observer.ObserverBase.html |   6 +-
 ...orch.ao.quantization.observer.PerAxis.html |   2 +-
 ...rch.ao.quantization.observer.PerBlock.html |   2 +-
 ...ion.observer.PerChannelMinMaxObserver.html |   4 +-
 ...rch.ao.quantization.observer.PerGroup.html |   2 +-
 ...torch.ao.quantization.observer.PerRow.html |   2 +-
 ...ch.ao.quantization.observer.PerTensor.html |   2 +-
 ...rch.ao.quantization.observer.PerToken.html |   2 +-
 ...tization.observer.PlaceholderObserver.html |   2 +-
 ...antization.observer.RecordingObserver.html |   2 +-
 ...ao.quantization.observer.TorchAODType.html |   2 +-
 ...quantization.observer.ZeroPointDomain.html |   2 +-
 ...ation.observer.default_debug_observer.html |   2 +-
 ...observer.default_placeholder_observer.html |   2 +-
 ....quantization.observer.get_block_size.html |   2 +-
 ...tion.observer.get_observer_state_dict.html |   2 +-
 ...ion.observer.load_observer_state_dict.html |   2 +-
 .../torch.ao.quantization.prepare.html        |   2 +-
 ...on.prepare_for_propagation_comparison.html |   2 +-
 .../torch.ao.quantization.prepare_qat.html    |   2 +-
 ...ch.ao.quantization.propagate_qconfig_.html |   2 +-
 ...n.pt2e.export_utils.model_is_exported.html |   2 +-
 ....lowering.lower_pt2e_quantized_to_x86.html |   2 +-
 ...torch.ao.quantization.qconfig.QConfig.html |   2 +-
 ...zation.qconfig_mapping.QConfigMapping.html |  16 +-
 ...pping.get_default_qat_qconfig_mapping.html |   2 +-
 ...g_mapping.get_default_qconfig_mapping.html |   2 +-
 .../torch.ao.quantization.quantize.html       |   2 +-
 ...orch.ao.quantization.quantize_dynamic.html |   2 +-
 ...o.quantization.quantize_fx.convert_fx.html |   2 +-
 ...h.ao.quantization.quantize_fx.fuse_fx.html |   2 +-
 ...o.quantization.quantize_fx.prepare_fx.html |   2 +-
 ...antization.quantize_fx.prepare_qat_fx.html |   2 +-
 .../torch.ao.quantization.quantize_qat.html   |   2 +-
 .../torch.ao.quantization.swap_module.html    |   2 +-
 ....are_deterministic_algorithms_enabled.html |   2 +-
 2.9/generated/torch.atleast_1d.html           |   2 +-
 2.9/generated/torch.atleast_2d.html           |   2 +-
 2.9/generated/torch.atleast_3d.html           |   2 +-
 .../torch.autograd.Function.backward.html     |   2 +-
 .../torch.autograd.Function.forward.html      |   2 +-
 .../torch.autograd.Function.jvp.html          |   2 +-
 .../torch.autograd.Function.vmap.html         |   2 +-
 2.9/generated/torch.autograd.backward.html    |   2 +-
 ...utograd.forward_ad.UnpackedDualTensor.html |   2 +-
 .../torch.autograd.forward_ad.dual_level.html |   2 +-
 ....autograd.forward_ad.enter_dual_level.html |   2 +-
 ...h.autograd.forward_ad.exit_dual_level.html |   2 +-
 .../torch.autograd.forward_ad.make_dual.html  |   2 +-
 ...torch.autograd.forward_ad.unpack_dual.html |   2 +-
 ...h.autograd.function.BackwardCFunction.html |  16 +-
 ...ograd.function.FunctionCtx.mark_dirty.html |   2 +-
 ...n.FunctionCtx.mark_non_differentiable.html |   2 +-
 ...unction.FunctionCtx.save_for_backward.html |   2 +-
 ...ion.FunctionCtx.set_materialize_grads.html |   2 +-
 ...rch.autograd.function.InplaceFunction.html |  24 +-
 ...ch.autograd.function.NestedIOFunction.html |  28 +-
 ...autograd.function.once_differentiable.html |   2 +-
 .../torch.autograd.functional.hessian.html    |   2 +-
 .../torch.autograd.functional.hvp.html        |   2 +-
 .../torch.autograd.functional.jacobian.html   |   2 +-
 .../torch.autograd.functional.jvp.html        |   2 +-
 .../torch.autograd.functional.vhp.html        |   2 +-
 .../torch.autograd.functional.vjp.html        |   2 +-
 2.9/generated/torch.autograd.grad.html        |   2 +-
 ...rch.autograd.grad_mode.inference_mode.html |   4 +-
 ...h.autograd.grad_mode.set_grad_enabled.html |   4 +-
 ....grad_mode.set_multithreading_enabled.html |   4 +-
 ...rch.autograd.gradcheck.GradcheckError.html |   2 +-
 .../torch.autograd.gradcheck.gradcheck.html   |   2 +-
 ...orch.autograd.gradcheck.gradgradcheck.html |   2 +-
 .../torch.autograd.graph.Node.metadata.html   |   2 +-
 .../torch.autograd.graph.Node.name.html       |   2 +-
 ...rch.autograd.graph.Node.register_hook.html |   2 +-
 ....autograd.graph.Node.register_prehook.html |   2 +-
 ...orch.autograd.graph.increment_version.html |   2 +-
 ...torch.autograd.profiler.EnforceUnique.html |   4 +-
 ...h.autograd.profiler.KinetoStepTracker.html |  10 +-
 .../torch.autograd.profiler.load_nvprof.html  |   2 +-
 ....autograd.profiler.parse_nvprof_trace.html |   2 +-
 ....profiler.profile.export_chrome_trace.html |   2 +-
 ...utograd.profiler.profile.key_averages.html |   2 +-
 ...tograd.profiler.profile.total_average.html |   2 +-
 ...rch.autograd.profiler.record_function.html |   2 +-
 ...torch.autograd.profiler_util.Interval.html |   4 +-
 ....autograd.profiler_util.MemRecordsAcc.html |   4 +-
 ...ch.autograd.profiler_util.StringTable.html |   2 +-
 2.9/generated/torch.block_diag.html           |   2 +-
 2.9/generated/torch.broadcast_shapes.html     |   2 +-
 2.9/generated/torch.broadcast_tensors.html    |   2 +-
 2.9/generated/torch.cartesian_prod.html       |   2 +-
 2.9/generated/torch.cdist.html                |   2 +-
 2.9/generated/torch.chain_matmul.html         |   2 +-
 2.9/generated/torch.compile.html              |   2 +-
 .../torch.compiled_with_cxx11_abi.html        |   2 +-
 .../torch.compiler.allow_in_graph.html        |   2 +-
 ...torch.compiler.assume_constant_result.html |   2 +-
 2.9/generated/torch.compiler.compile.html     |   2 +-
 ...ch.compiler.cudagraph_mark_step_begin.html |   2 +-
 2.9/generated/torch.compiler.disable.html     |   2 +-
 .../torch.compiler.is_compiling.html          |   2 +-
 .../torch.compiler.is_dynamo_compiling.html   |   2 +-
 .../torch.compiler.is_exporting.html          |   2 +-
 ...ch.compiler.keep_tensor_guards_unsafe.html |   2 +-
 .../torch.compiler.list_backends.html         |   2 +-
 .../torch.compiler.nested_compile_region.html |   2 +-
 2.9/generated/torch.compiler.reset.html       |   2 +-
 ...compiler.set_enable_guard_collectives.html |   2 +-
 2.9/generated/torch.compiler.set_stance.html  |   2 +-
 ...r.skip_guard_on_all_nn_modules_unsafe.html |   2 +-
 ...compiler.skip_guard_on_globals_unsafe.html |   2 +-
 ...ip_guard_on_inbuilt_nn_modules_unsafe.html |   2 +-
 .../torch.compiler.substitute_in_graph.html   |   2 +-
 2.9/generated/torch.cond.html                 |   2 +-
 2.9/generated/torch.cpu.Stream.html           |   2 +-
 2.9/generated/torch.cpu.StreamContext.html    |   2 +-
 2.9/generated/torch.cpu.current_device.html   |   2 +-
 2.9/generated/torch.cpu.current_stream.html   |   2 +-
 2.9/generated/torch.cpu.device_count.html     |   2 +-
 2.9/generated/torch.cpu.is_available.html     |   2 +-
 2.9/generated/torch.cpu.set_device.html       |   2 +-
 2.9/generated/torch.cpu.stream.html           |   2 +-
 2.9/generated/torch.cpu.synchronize.html      |   2 +-
 2.9/generated/torch.cuda.CUDAGraph.html       |  22 +-
 2.9/generated/torch.cuda.Event.html           |  16 +-
 2.9/generated/torch.cuda.ExternalStream.html  |  12 +-
 2.9/generated/torch.cuda.Stream.html          |  12 +-
 2.9/generated/torch.cuda.StreamContext.html   |   2 +-
 .../torch.cuda.can_device_access_peer.html    |   2 +-
 2.9/generated/torch.cuda.clock_rate.html      |   2 +-
 2.9/generated/torch.cuda.comm.broadcast.html  |   2 +-
 .../torch.cuda.comm.broadcast_coalesced.html  |   2 +-
 2.9/generated/torch.cuda.comm.gather.html     |   2 +-
 2.9/generated/torch.cuda.comm.reduce_add.html |   2 +-
 .../torch.cuda.comm.reduce_add_coalesced.html |   2 +-
 2.9/generated/torch.cuda.comm.scatter.html    |   2 +-
 2.9/generated/torch.cuda.cudart.html          |   2 +-
 .../torch.cuda.current_blas_handle.html       |   2 +-
 2.9/generated/torch.cuda.current_device.html  |   2 +-
 2.9/generated/torch.cuda.current_stream.html  |   2 +-
 2.9/generated/torch.cuda.default_stream.html  |   2 +-
 2.9/generated/torch.cuda.device.html          |   2 +-
 2.9/generated/torch.cuda.device_count.html    |   2 +-
 .../torch.cuda.device_memory_used.html        |   2 +-
 2.9/generated/torch.cuda.device_of.html       |   2 +-
 2.9/generated/torch.cuda.gds.GdsFile.html     |  10 +-
 .../torch.cuda.gds.gds_deregister_buffer.html |   2 +-
 .../torch.cuda.gds.gds_register_buffer.html   |   2 +-
 2.9/generated/torch.cuda.get_arch_list.html   |   2 +-
 .../torch.cuda.get_device_capability.html     |   2 +-
 2.9/generated/torch.cuda.get_device_name.html |   2 +-
 .../torch.cuda.get_device_properties.html     |   2 +-
 .../torch.cuda.get_gencode_flags.html         |   2 +-
 2.9/generated/torch.cuda.get_rng_state.html   |   2 +-
 .../torch.cuda.get_rng_state_all.html         |   2 +-
 .../torch.cuda.get_stream_from_external.html  |   2 +-
 .../torch.cuda.get_sync_debug_mode.html       |   2 +-
 2.9/generated/torch.cuda.graph.html           |   2 +-
 .../torch.cuda.graph_pool_handle.html         |   2 +-
 2.9/generated/torch.cuda.init.html            |   2 +-
 2.9/generated/torch.cuda.initial_seed.html    |   2 +-
 2.9/generated/torch.cuda.ipc_collect.html     |   2 +-
 2.9/generated/torch.cuda.is_available.html    |   2 +-
 ...orch.cuda.is_current_stream_capturing.html |   2 +-
 2.9/generated/torch.cuda.is_initialized.html  |   2 +-
 .../torch.cuda.is_tf32_supported.html         |   2 +-
 .../torch.cuda.jiterator._create_jit_fn.html  |   2 +-
 ...jiterator._create_multi_output_jit_fn.html |   2 +-
 .../torch.cuda.make_graphed_callables.html    |   2 +-
 2.9/generated/torch.cuda.manual_seed.html     |   2 +-
 2.9/generated/torch.cuda.manual_seed_all.html |   2 +-
 ...ch.cuda.memory.CUDAPluggableAllocator.html |   2 +-
 2.9/generated/torch.cuda.memory.MemPool.html  |   6 +-
 ...h.cuda.memory.caching_allocator_alloc.html |   2 +-
 ....cuda.memory.caching_allocator_delete.html |   2 +-
 ....cuda.memory.caching_allocator_enable.html |   2 +-
 ....cuda.memory.change_current_allocator.html |   2 +-
 .../torch.cuda.memory.empty_cache.html        |   2 +-
 ...rch.cuda.memory.get_allocator_backend.html |   2 +-
 ...emory.get_per_process_memory_fraction.html |   2 +-
 .../torch.cuda.memory.host_memory_stats.html  |   2 +-
 ...mory.host_memory_stats_as_nested_dict.html |   2 +-
 .../torch.cuda.memory.list_gpu_processes.html |   2 +-
 ...orch.cuda.memory.max_memory_allocated.html |   2 +-
 .../torch.cuda.memory.max_memory_cached.html  |   2 +-
 ...torch.cuda.memory.max_memory_reserved.html |   2 +-
 .../torch.cuda.memory.mem_get_info.html       |   2 +-
 .../torch.cuda.memory.memory_allocated.html   |   2 +-
 .../torch.cuda.memory.memory_cached.html      |   2 +-
 .../torch.cuda.memory.memory_reserved.html    |   2 +-
 .../torch.cuda.memory.memory_snapshot.html    |   2 +-
 .../torch.cuda.memory.memory_stats.html       |   2 +-
 ...da.memory.memory_stats_as_nested_dict.html |   2 +-
 .../torch.cuda.memory.memory_summary.html     |   2 +-
 ...y.reset_accumulated_host_memory_stats.html |   2 +-
 ...memory.reset_accumulated_memory_stats.html |   2 +-
 ...uda.memory.reset_max_memory_allocated.html |   2 +-
 ...h.cuda.memory.reset_max_memory_cached.html |   2 +-
 ...a.memory.reset_peak_host_memory_stats.html |   2 +-
 ...h.cuda.memory.reset_peak_memory_stats.html |   2 +-
 ...emory.set_per_process_memory_fraction.html |   2 +-
 2.9/generated/torch.cuda.memory_usage.html    |   2 +-
 2.9/generated/torch.cuda.nvtx.mark.html       |   2 +-
 2.9/generated/torch.cuda.nvtx.range.html      |   2 +-
 2.9/generated/torch.cuda.nvtx.range_pop.html  |   2 +-
 2.9/generated/torch.cuda.nvtx.range_push.html |   2 +-
 2.9/generated/torch.cuda.power_draw.html      |   2 +-
 2.9/generated/torch.cuda.seed.html            |   2 +-
 2.9/generated/torch.cuda.seed_all.html        |   2 +-
 2.9/generated/torch.cuda.set_device.html      |   2 +-
 2.9/generated/torch.cuda.set_rng_state.html   |   2 +-
 .../torch.cuda.set_rng_state_all.html         |   2 +-
 2.9/generated/torch.cuda.set_stream.html      |   2 +-
 .../torch.cuda.set_sync_debug_mode.html       |   2 +-
 2.9/generated/torch.cuda.stream.html          |   2 +-
 2.9/generated/torch.cuda.synchronize.html     |   2 +-
 2.9/generated/torch.cuda.temperature.html     |   2 +-
 2.9/generated/torch.cuda.utilization.html     |   2 +-
 2.9/generated/torch.einsum.html               |   2 +-
 2.9/generated/torch.enable_grad.html          |   2 +-
 2.9/generated/torch.from_dlpack.html          |   2 +-
 2.9/generated/torch.func.debug_unwrap.html    |   2 +-
 2.9/generated/torch.func.functional_call.html |   2 +-
 2.9/generated/torch.func.functionalize.html   |   2 +-
 2.9/generated/torch.func.grad.html            |   2 +-
 2.9/generated/torch.func.grad_and_value.html  |   2 +-
 2.9/generated/torch.func.hessian.html         |   2 +-
 2.9/generated/torch.func.jacfwd.html          |   2 +-
 2.9/generated/torch.func.jacrev.html          |   2 +-
 2.9/generated/torch.func.jvp.html             |   2 +-
 2.9/generated/torch.func.linearize.html       |   2 +-
 ....func.replace_all_batch_norm_modules_.html |   2 +-
 .../torch.func.stack_module_state.html        |   2 +-
 2.9/generated/torch.func.vjp.html             |   2 +-
 2.9/generated/torch.func.vmap.html            |   2 +-
 .../torch.functional.align_tensors.html       |   2 +-
 .../torch.functional.atleast_1d.html          |   2 +-
 .../torch.functional.atleast_2d.html          |   2 +-
 .../torch.functional.atleast_3d.html          |   2 +-
 .../torch.functional.block_diag.html          |   2 +-
 .../torch.functional.broadcast_shapes.html    |   2 +-
 .../torch.functional.broadcast_tensors.html   |   2 +-
 .../torch.functional.cartesian_prod.html      |   2 +-
 2.9/generated/torch.functional.cdist.html     |   2 +-
 .../torch.functional.chain_matmul.html        |   2 +-
 2.9/generated/torch.functional.einsum.html    |   2 +-
 2.9/generated/torch.functional.lu.html        |   2 +-
 2.9/generated/torch.functional.meshgrid.html  |   2 +-
 2.9/generated/torch.functional.norm.html      |   2 +-
 2.9/generated/torch.functional.split.html     |   2 +-
 2.9/generated/torch.functional.stft.html      |   2 +-
 2.9/generated/torch.functional.tensordot.html |   2 +-
 2.9/generated/torch.functional.unique.html    |   2 +-
 .../torch.functional.unique_consecutive.html  |   2 +-
 .../torch.functional.unravel_index.html       |   2 +-
 ...erimental.proxy_tensor.get_proxy_mode.html |   2 +-
 ...ntal.proxy_tensor.handle_sym_dispatch.html |   2 +-
 ....fx.experimental.proxy_tensor.make_fx.html |   2 +-
 ...l.proxy_tensor.maybe_disable_thunkify.html |   2 +-
 ...al.proxy_tensor.maybe_enable_thunkify.html |   2 +-
 ...imental.symbolic_shapes.CallMethodKey.html |   4 +-
 ...imental.symbolic_shapes.ConvertIntKey.html |   4 +-
 ...mental.symbolic_shapes.DimConstraints.html |  14 +-
 ...perimental.symbolic_shapes.DimDynamic.html |   2 +-
 ...erimental.symbolic_shapes.DivideByKey.html |   4 +-
 ...al.symbolic_shapes.EqualityConstraint.html |   2 +-
 ...mental.symbolic_shapes.InnerTensorKey.html |   4 +-
 ...bolic_shapes.PropagateUnbackedSymInts.html |  26 +-
 ...mbolic_shapes.RelaxedUnspecConstraint.html |   2 +-
 ...experimental.symbolic_shapes.ShapeEnv.html |  82 +--
 ...ntal.symbolic_shapes.ShapeEnvSettings.html |   2 +-
 ...mental.symbolic_shapes.Specialization.html |   2 +-
 ...mbolic_shapes.StatefulSymbolicContext.html |   2 +-
 ...bolic_shapes.StatelessSymbolicContext.html |   2 +-
 ...ymbolic_shapes.StrictMinMaxConstraint.html |   4 +-
 ...mbolic_shapes.SubclassSymbolicContext.html |   2 +-
 ...ental.symbolic_shapes.SymbolicContext.html |   2 +-
 ...ymbolic_shapes.canonicalize_bool_expr.html |   2 +-
 ...ntal.symbolic_shapes.check_consistent.html |   2 +-
 ...olic_shapes.compute_unbacked_bindings.html |   2 +-
 ...ental.symbolic_shapes.constrain_range.html |   2 +-
 ...ental.symbolic_shapes.constrain_unify.html |   2 +-
 ...mental.symbolic_shapes.guard_or_false.html |   2 +-
 ...imental.symbolic_shapes.guard_or_true.html |   2 +-
 ....symbolic_shapes.guard_size_oblivious.html |   2 +-
 ...ntal.symbolic_shapes.has_free_symbols.html |   2 +-
 ...olic_shapes.has_free_unbacked_symbols.html |   2 +-
 ...ntal.symbolic_shapes.has_static_value.html |   2 +-
 ...experimental.symbolic_shapes.hint_int.html |   2 +-
 ...ntal.symbolic_shapes.is_accessor_node.html |   2 +-
 ...ntal.symbolic_shapes.is_concrete_bool.html |   2 +-
 ...tal.symbolic_shapes.is_concrete_float.html |   2 +-
 ...ental.symbolic_shapes.is_concrete_int.html |   2 +-
 ...xperimental.symbolic_shapes.lru_cache.html |   2 +-
 ...ental.symbolic_shapes.rebind_unbacked.html |   2 +-
 ...olic_shapes.resolve_unbacked_bindings.html |   2 +-
 ...ymbolic_shapes.statically_known_false.html |   2 +-
 ...symbolic_shapes.statically_known_true.html |   2 +-
 ....experimental.symbolic_shapes.sym_and.html |   2 +-
 ...x.experimental.symbolic_shapes.sym_eq.html |   2 +-
 ...x.experimental.symbolic_shapes.sym_or.html |   2 +-
 2.9/generated/torch.get_default_device.html   |   2 +-
 .../torch.get_deterministic_debug_mode.html   |   2 +-
 2.9/generated/torch.get_device_module.html    |   2 +-
 .../torch.get_float32_matmul_precision.html   |   2 +-
 2.9/generated/torch.get_rng_state.html        |   2 +-
 2.9/generated/torch.initial_seed.html         |   2 +-
 ...ministic_algorithms_warn_only_enabled.html |   2 +-
 2.9/generated/torch.is_storage.html           |   2 +-
 2.9/generated/torch.is_tensor.html            |   2 +-
 .../torch.is_warn_always_enabled.html         |   2 +-
 2.9/generated/torch.jit.ScriptModule.html     | 110 ++--
 2.9/generated/torch.jit.annotate.html         |   2 +-
 .../torch.jit.enable_onednn_fusion.html       |   2 +-
 2.9/generated/torch.jit.fork.html             |   2 +-
 2.9/generated/torch.jit.freeze.html           |   2 +-
 2.9/generated/torch.jit.ignore.html           |   2 +-
 2.9/generated/torch.jit.interface.html        |   2 +-
 2.9/generated/torch.jit.isinstance.html       |   2 +-
 2.9/generated/torch.jit.load.html             |   2 +-
 .../torch.jit.onednn_fusion_enabled.html      |   2 +-
 .../torch.jit.optimize_for_inference.html     |   2 +-
 2.9/generated/torch.jit.save.html             |   2 +-
 2.9/generated/torch.jit.script.html           |   2 +-
 .../torch.jit.script_if_tracing.html          |   2 +-
 .../torch.jit.set_fusion_strategy.html        |   2 +-
 2.9/generated/torch.jit.strict_fusion.html    |   2 +-
 2.9/generated/torch.jit.trace.html            |   2 +-
 2.9/generated/torch.jit.trace_module.html     |   2 +-
 2.9/generated/torch.jit.unused.html           |   2 +-
 2.9/generated/torch.jit.wait.html             |   2 +-
 2.9/generated/torch.load.html                 |   2 +-
 2.9/generated/torch.lobpcg.html               |   2 +-
 2.9/generated/torch.lu.html                   |   2 +-
 2.9/generated/torch.manual_seed.html          |   2 +-
 2.9/generated/torch.meshgrid.html             |   2 +-
 2.9/generated/torch.mps.compile_shader.html   |   2 +-
 .../torch.mps.current_allocated_memory.html   |   2 +-
 2.9/generated/torch.mps.device_count.html     |   2 +-
 .../torch.mps.driver_allocated_memory.html    |   2 +-
 2.9/generated/torch.mps.empty_cache.html      |   2 +-
 2.9/generated/torch.mps.event.Event.html      |  12 +-
 2.9/generated/torch.mps.get_rng_state.html    |   2 +-
 2.9/generated/torch.mps.manual_seed.html      |   2 +-
 ...torch.mps.profiler.is_capturing_metal.html |   2 +-
 ...mps.profiler.is_metal_capture_enabled.html |   2 +-
 .../torch.mps.profiler.metal_capture.html     |   2 +-
 2.9/generated/torch.mps.profiler.profile.html |   2 +-
 2.9/generated/torch.mps.profiler.start.html   |   2 +-
 2.9/generated/torch.mps.profiler.stop.html    |   2 +-
 .../torch.mps.recommended_max_memory.html     |   2 +-
 2.9/generated/torch.mps.seed.html             |   2 +-
 ...h.mps.set_per_process_memory_fraction.html |   2 +-
 2.9/generated/torch.mps.set_rng_state.html    |   2 +-
 2.9/generated/torch.mps.synchronize.html      |   2 +-
 .../torch.mtia.DeferredMtiaCallError.html     |   2 +-
 2.9/generated/torch.mtia.StreamContext.html   |   2 +-
 ...ch.mtia.attach_out_of_memory_observer.html |   2 +-
 2.9/generated/torch.mtia.current_device.html  |   2 +-
 2.9/generated/torch.mtia.current_stream.html  |   2 +-
 2.9/generated/torch.mtia.default_stream.html  |   2 +-
 2.9/generated/torch.mtia.device.html          |   2 +-
 2.9/generated/torch.mtia.device_count.html    |   2 +-
 2.9/generated/torch.mtia.empty_cache.html     |   2 +-
 .../torch.mtia.get_device_capability.html     |   2 +-
 2.9/generated/torch.mtia.get_rng_state.html   |   2 +-
 2.9/generated/torch.mtia.init.html            |   2 +-
 2.9/generated/torch.mtia.is_available.html    |   2 +-
 2.9/generated/torch.mtia.is_initialized.html  |   2 +-
 .../torch.mtia.memory.memory_allocated.html   |   2 +-
 .../torch.mtia.memory.memory_stats.html       |   2 +-
 2.9/generated/torch.mtia.memory_stats.html    |   2 +-
 .../torch.mtia.record_memory_history.html     |   2 +-
 2.9/generated/torch.mtia.set_device.html      |   2 +-
 2.9/generated/torch.mtia.set_rng_state.html   |   2 +-
 2.9/generated/torch.mtia.set_stream.html      |   2 +-
 2.9/generated/torch.mtia.snapshot.html        |   2 +-
 2.9/generated/torch.mtia.stream.html          |   2 +-
 2.9/generated/torch.mtia.synchronize.html     |   2 +-
 2.9/generated/torch.nn.AdaptiveAvgPool1d.html |   4 +-
 2.9/generated/torch.nn.AdaptiveAvgPool2d.html |   4 +-
 2.9/generated/torch.nn.AdaptiveAvgPool3d.html |   4 +-
 .../torch.nn.AdaptiveLogSoftmaxWithLoss.html  |  10 +-
 2.9/generated/torch.nn.AdaptiveMaxPool1d.html |   4 +-
 2.9/generated/torch.nn.AdaptiveMaxPool2d.html |   4 +-
 2.9/generated/torch.nn.AdaptiveMaxPool3d.html |   4 +-
 2.9/generated/torch.nn.AlphaDropout.html      |   4 +-
 2.9/generated/torch.nn.AvgPool1d.html         |   4 +-
 2.9/generated/torch.nn.AvgPool2d.html         |   4 +-
 2.9/generated/torch.nn.AvgPool3d.html         |   4 +-
 2.9/generated/torch.nn.BCELoss.html           |   4 +-
 2.9/generated/torch.nn.BCEWithLogitsLoss.html |   4 +-
 2.9/generated/torch.nn.BatchNorm1d.html       |   2 +-
 2.9/generated/torch.nn.BatchNorm2d.html       |   2 +-
 2.9/generated/torch.nn.BatchNorm3d.html       |   2 +-
 2.9/generated/torch.nn.Bilinear.html          |   8 +-
 2.9/generated/torch.nn.CELU.html              |   6 +-
 2.9/generated/torch.nn.CTCLoss.html           |   4 +-
 2.9/generated/torch.nn.ChannelShuffle.html    |   6 +-
 2.9/generated/torch.nn.CircularPad1d.html     |   2 +-
 2.9/generated/torch.nn.CircularPad2d.html     |   2 +-
 2.9/generated/torch.nn.CircularPad3d.html     |   2 +-
 2.9/generated/torch.nn.ConstantPad1d.html     |   2 +-
 2.9/generated/torch.nn.ConstantPad2d.html     |   2 +-
 2.9/generated/torch.nn.ConstantPad3d.html     |   2 +-
 2.9/generated/torch.nn.Conv1d.html            |   2 +-
 2.9/generated/torch.nn.Conv2d.html            |   2 +-
 2.9/generated/torch.nn.Conv3d.html            |   2 +-
 2.9/generated/torch.nn.ConvTranspose1d.html   |   2 +-
 2.9/generated/torch.nn.ConvTranspose2d.html   |   4 +-
 2.9/generated/torch.nn.ConvTranspose3d.html   |   2 +-
 .../torch.nn.CosineEmbeddingLoss.html         |   4 +-
 2.9/generated/torch.nn.CosineSimilarity.html  |   4 +-
 2.9/generated/torch.nn.CrossEntropyLoss.html  |   4 +-
 2.9/generated/torch.nn.DataParallel.html      |   2 +-
 2.9/generated/torch.nn.Dropout.html           |   4 +-
 2.9/generated/torch.nn.Dropout1d.html         |   4 +-
 2.9/generated/torch.nn.Dropout2d.html         |   4 +-
 2.9/generated/torch.nn.Dropout3d.html         |   4 +-
 2.9/generated/torch.nn.ELU.html               |   6 +-
 2.9/generated/torch.nn.Embedding.html         |   4 +-
 2.9/generated/torch.nn.EmbeddingBag.html      |   6 +-
 .../torch.nn.FeatureAlphaDropout.html         |   4 +-
 2.9/generated/torch.nn.Fold.html              |   6 +-
 .../torch.nn.FractionalMaxPool2d.html         |   2 +-
 .../torch.nn.FractionalMaxPool3d.html         |   2 +-
 2.9/generated/torch.nn.GELU.html              |   6 +-
 2.9/generated/torch.nn.GLU.html               |   6 +-
 2.9/generated/torch.nn.GRU.html               |   2 +-
 2.9/generated/torch.nn.GRUCell.html           |   2 +-
 2.9/generated/torch.nn.GaussianNLLLoss.html   |   4 +-
 2.9/generated/torch.nn.GroupNorm.html         |   2 +-
 2.9/generated/torch.nn.Hardshrink.html        |   6 +-
 2.9/generated/torch.nn.Hardsigmoid.html       |   4 +-
 2.9/generated/torch.nn.Hardswish.html         |   4 +-
 2.9/generated/torch.nn.Hardtanh.html          |   6 +-
 .../torch.nn.HingeEmbeddingLoss.html          |   4 +-
 2.9/generated/torch.nn.HuberLoss.html         |   4 +-
 2.9/generated/torch.nn.Identity.html          |   4 +-
 2.9/generated/torch.nn.InstanceNorm1d.html    |   2 +-
 2.9/generated/torch.nn.InstanceNorm2d.html    |   2 +-
 2.9/generated/torch.nn.InstanceNorm3d.html    |   2 +-
 2.9/generated/torch.nn.KLDivLoss.html         |   4 +-
 2.9/generated/torch.nn.L1Loss.html            |   4 +-
 2.9/generated/torch.nn.LPPool1d.html          |   4 +-
 2.9/generated/torch.nn.LPPool2d.html          |   4 +-
 2.9/generated/torch.nn.LPPool3d.html          |   4 +-
 2.9/generated/torch.nn.LSTM.html              |   2 +-
 2.9/generated/torch.nn.LSTMCell.html          |   2 +-
 2.9/generated/torch.nn.LayerNorm.html         |   2 +-
 2.9/generated/torch.nn.LazyBatchNorm1d.html   |   4 +-
 2.9/generated/torch.nn.LazyBatchNorm2d.html   |   4 +-
 2.9/generated/torch.nn.LazyBatchNorm3d.html   |   4 +-
 2.9/generated/torch.nn.LazyConv1d.html        |   4 +-
 2.9/generated/torch.nn.LazyConv2d.html        |   4 +-
 2.9/generated/torch.nn.LazyConv3d.html        |   4 +-
 .../torch.nn.LazyConvTranspose1d.html         |   4 +-
 .../torch.nn.LazyConvTranspose2d.html         |   4 +-
 .../torch.nn.LazyConvTranspose3d.html         |   4 +-
 .../torch.nn.LazyInstanceNorm1d.html          |   4 +-
 .../torch.nn.LazyInstanceNorm2d.html          |   4 +-
 .../torch.nn.LazyInstanceNorm3d.html          |   4 +-
 2.9/generated/torch.nn.LazyLinear.html        |   8 +-
 2.9/generated/torch.nn.LeakyReLU.html         |   6 +-
 2.9/generated/torch.nn.Linear.html            |   8 +-
 2.9/generated/torch.nn.LocalResponseNorm.html |   6 +-
 2.9/generated/torch.nn.LogSigmoid.html        |   4 +-
 2.9/generated/torch.nn.LogSoftmax.html        |   6 +-
 2.9/generated/torch.nn.MSELoss.html           |   4 +-
 2.9/generated/torch.nn.MarginRankingLoss.html |   4 +-
 2.9/generated/torch.nn.MaxPool1d.html         |   4 +-
 2.9/generated/torch.nn.MaxPool2d.html         |   4 +-
 2.9/generated/torch.nn.MaxPool3d.html         |   4 +-
 2.9/generated/torch.nn.MaxUnpool1d.html       |   4 +-
 2.9/generated/torch.nn.MaxUnpool2d.html       |   4 +-
 2.9/generated/torch.nn.MaxUnpool3d.html       |   4 +-
 2.9/generated/torch.nn.Mish.html              |   6 +-
 2.9/generated/torch.nn.Module.html            | 110 ++--
 2.9/generated/torch.nn.ModuleDict.html        |  14 +-
 2.9/generated/torch.nn.ModuleList.html        |   8 +-
 .../torch.nn.MultiLabelMarginLoss.html        |   4 +-
 .../torch.nn.MultiLabelSoftMarginLoss.html    |   4 +-
 2.9/generated/torch.nn.MultiMarginLoss.html   |   4 +-
 .../torch.nn.MultiheadAttention.html          |   6 +-
 2.9/generated/torch.nn.NLLLoss.html           |   4 +-
 2.9/generated/torch.nn.PReLU.html             |   8 +-
 2.9/generated/torch.nn.PairwiseDistance.html  |   4 +-
 2.9/generated/torch.nn.ParameterDict.html     |  24 +-
 2.9/generated/torch.nn.ParameterList.html     |   8 +-
 2.9/generated/torch.nn.PixelShuffle.html      |   6 +-
 2.9/generated/torch.nn.PixelUnshuffle.html    |   6 +-
 2.9/generated/torch.nn.PoissonNLLLoss.html    |   4 +-
 2.9/generated/torch.nn.RMSNorm.html           |   8 +-
 2.9/generated/torch.nn.RNN.html               |   4 +-
 2.9/generated/torch.nn.RNNBase.html           |   4 +-
 2.9/generated/torch.nn.RNNCell.html           |   2 +-
 2.9/generated/torch.nn.RReLU.html             |   6 +-
 2.9/generated/torch.nn.ReLU.html              |   6 +-
 2.9/generated/torch.nn.ReLU6.html             |   4 +-
 2.9/generated/torch.nn.ReflectionPad1d.html   |   2 +-
 2.9/generated/torch.nn.ReflectionPad2d.html   |   2 +-
 2.9/generated/torch.nn.ReflectionPad3d.html   |   2 +-
 2.9/generated/torch.nn.ReplicationPad1d.html  |   2 +-
 2.9/generated/torch.nn.ReplicationPad2d.html  |   2 +-
 2.9/generated/torch.nn.ReplicationPad3d.html  |   2 +-
 2.9/generated/torch.nn.SELU.html              |   6 +-
 2.9/generated/torch.nn.Sequential.html        |  12 +-
 2.9/generated/torch.nn.SiLU.html              |   6 +-
 2.9/generated/torch.nn.Sigmoid.html           |   4 +-
 2.9/generated/torch.nn.SmoothL1Loss.html      |   4 +-
 2.9/generated/torch.nn.SoftMarginLoss.html    |   4 +-
 2.9/generated/torch.nn.Softmax.html           |   6 +-
 2.9/generated/torch.nn.Softmax2d.html         |   4 +-
 2.9/generated/torch.nn.Softmin.html           |   6 +-
 2.9/generated/torch.nn.Softplus.html          |   6 +-
 2.9/generated/torch.nn.Softshrink.html        |   6 +-
 2.9/generated/torch.nn.Softsign.html          |   4 +-
 2.9/generated/torch.nn.SyncBatchNorm.html     |   6 +-
 2.9/generated/torch.nn.Tanh.html              |   4 +-
 2.9/generated/torch.nn.Tanhshrink.html        |   4 +-
 2.9/generated/torch.nn.Threshold.html         |   6 +-
 2.9/generated/torch.nn.Transformer.html       |   6 +-
 .../torch.nn.TransformerDecoder.html          |   4 +-
 .../torch.nn.TransformerDecoderLayer.html     |   4 +-
 .../torch.nn.TransformerEncoder.html          |   4 +-
 .../torch.nn.TransformerEncoderLayer.html     |   4 +-
 2.9/generated/torch.nn.TripletMarginLoss.html |   4 +-
 ...orch.nn.TripletMarginWithDistanceLoss.html |   4 +-
 2.9/generated/torch.nn.Unfold.html            |   6 +-
 2.9/generated/torch.nn.Upsample.html          |   6 +-
 .../torch.nn.UpsamplingBilinear2d.html        |   2 +-
 .../torch.nn.UpsamplingNearest2d.html         |   2 +-
 2.9/generated/torch.nn.ZeroPad1d.html         |   4 +-
 2.9/generated/torch.nn.ZeroPad2d.html         |   4 +-
 2.9/generated/torch.nn.ZeroPad3d.html         |   4 +-
 .../torch.nn.attention.bias.CausalBias.html   |   2 +-
 ...torch.nn.attention.bias.CausalVariant.html |   2 +-
 ....nn.attention.bias.causal_lower_right.html |   2 +-
 ...h.nn.attention.bias.causal_upper_left.html |   2 +-
 .../torch.nn.attention.sdpa_kernel.html       |   2 +-
 2.9/generated/torch.nn.factory_kwargs.html    |   2 +-
 ...rch.nn.functional.adaptive_avg_pool2d.html |   2 +-
 ...rch.nn.functional.adaptive_avg_pool3d.html |   2 +-
 ...rch.nn.functional.adaptive_max_pool1d.html |   2 +-
 ...rch.nn.functional.adaptive_max_pool2d.html |   2 +-
 ...rch.nn.functional.adaptive_max_pool3d.html |   2 +-
 .../torch.nn.functional.affine_grid.html      |   2 +-
 .../torch.nn.functional.alpha_dropout.html    |   2 +-
 .../torch.nn.functional.batch_norm.html       |   2 +-
 ...ch.nn.functional.binary_cross_entropy.html |   2 +-
 ...onal.binary_cross_entropy_with_logits.html |   2 +-
 2.9/generated/torch.nn.functional.celu.html   |   2 +-
 ...h.nn.functional.cosine_embedding_loss.html |   2 +-
 .../torch.nn.functional.cross_entropy.html    |   2 +-
 .../torch.nn.functional.ctc_loss.html         |   2 +-
 .../torch.nn.functional.dropout.html          |   2 +-
 .../torch.nn.functional.dropout1d.html        |   2 +-
 .../torch.nn.functional.dropout2d.html        |   2 +-
 .../torch.nn.functional.dropout3d.html        |   2 +-
 2.9/generated/torch.nn.functional.elu.html    |   2 +-
 .../torch.nn.functional.embedding.html        |   2 +-
 .../torch.nn.functional.embedding_bag.html    |   2 +-
 ...h.nn.functional.feature_alpha_dropout.html |   2 +-
 2.9/generated/torch.nn.functional.fold.html   |   2 +-
 ...h.nn.functional.fractional_max_pool2d.html |   2 +-
 ...h.nn.functional.fractional_max_pool3d.html |   2 +-
 ...torch.nn.functional.gaussian_nll_loss.html |   2 +-
 2.9/generated/torch.nn.functional.glu.html    |   2 +-
 .../torch.nn.functional.grid_sample.html      |   2 +-
 .../torch.nn.functional.group_norm.html       |   2 +-
 .../torch.nn.functional.gumbel_softmax.html   |   2 +-
 .../torch.nn.functional.hardsigmoid.html      |   2 +-
 .../torch.nn.functional.hardswish.html        |   2 +-
 .../torch.nn.functional.hardtanh.html         |   2 +-
 ...ch.nn.functional.hinge_embedding_loss.html |   2 +-
 .../torch.nn.functional.huber_loss.html       |   2 +-
 .../torch.nn.functional.instance_norm.html    |   2 +-
 .../torch.nn.functional.interpolate.html      |   2 +-
 2.9/generated/torch.nn.functional.kl_div.html |   2 +-
 .../torch.nn.functional.l1_loss.html          |   2 +-
 .../torch.nn.functional.layer_norm.html       |   2 +-
 .../torch.nn.functional.leaky_relu.html       |   2 +-
 ...rch.nn.functional.local_response_norm.html |   2 +-
 .../torch.nn.functional.log_softmax.html      |   2 +-
 .../torch.nn.functional.lp_pool1d.html        |   2 +-
 .../torch.nn.functional.lp_pool2d.html        |   2 +-
 .../torch.nn.functional.lp_pool3d.html        |   2 +-
 ...rch.nn.functional.margin_ranking_loss.html |   2 +-
 .../torch.nn.functional.max_pool1d.html       |   2 +-
 .../torch.nn.functional.max_pool2d.html       |   2 +-
 .../torch.nn.functional.max_pool3d.html       |   2 +-
 .../torch.nn.functional.max_unpool1d.html     |   2 +-
 .../torch.nn.functional.max_unpool2d.html     |   2 +-
 .../torch.nn.functional.max_unpool3d.html     |   2 +-
 2.9/generated/torch.nn.functional.mish.html   |   2 +-
 .../torch.nn.functional.mse_loss.html         |   2 +-
 ...torch.nn.functional.multi_margin_loss.html |   2 +-
 ....nn.functional.multilabel_margin_loss.html |   2 +-
 ...unctional.multilabel_soft_margin_loss.html |   2 +-
 .../torch.nn.functional.nll_loss.html         |   2 +-
 .../torch.nn.functional.normalize.html        |   2 +-
 2.9/generated/torch.nn.functional.pad.html    |   2 +-
 .../torch.nn.functional.poisson_nll_loss.html |   2 +-
 2.9/generated/torch.nn.functional.relu.html   |   2 +-
 2.9/generated/torch.nn.functional.relu6.html  |   2 +-
 .../torch.nn.functional.rms_norm.html         |   2 +-
 2.9/generated/torch.nn.functional.rrelu.html  |   2 +-
 2.9/generated/torch.nn.functional.selu.html   |   2 +-
 .../torch.nn.functional.sigmoid.html          |   2 +-
 2.9/generated/torch.nn.functional.silu.html   |   2 +-
 .../torch.nn.functional.smooth_l1_loss.html   |   2 +-
 .../torch.nn.functional.soft_margin_loss.html |   2 +-
 .../torch.nn.functional.softmax.html          |   2 +-
 .../torch.nn.functional.softmin.html          |   2 +-
 .../torch.nn.functional.softsign.html         |   2 +-
 2.9/generated/torch.nn.functional.tanh.html   |   2 +-
 .../torch.nn.functional.tanhshrink.html       |   2 +-
 .../torch.nn.functional.threshold.html        |   2 +-
 ...ional.torch.nn.parallel.data_parallel.html |   2 +-
 ...rch.nn.functional.triplet_margin_loss.html |   2 +-
 ...nal.triplet_margin_with_distance_loss.html |   2 +-
 2.9/generated/torch.nn.functional.unfold.html |   2 +-
 .../torch.nn.functional.upsample.html         |   2 +-
 ...torch.nn.functional.upsample_bilinear.html |   2 +-
 .../torch.nn.functional.upsample_nearest.html |   2 +-
 .../torch.nn.modules.activation.CELU.html     |   6 +-
 .../torch.nn.modules.activation.ELU.html      |   6 +-
 .../torch.nn.modules.activation.GELU.html     |   6 +-
 .../torch.nn.modules.activation.GLU.html      |   6 +-
 ...orch.nn.modules.activation.Hardshrink.html |   6 +-
 ...rch.nn.modules.activation.Hardsigmoid.html |   4 +-
 ...torch.nn.modules.activation.Hardswish.html |   4 +-
 .../torch.nn.modules.activation.Hardtanh.html |   6 +-
 ...torch.nn.modules.activation.LeakyReLU.html |   6 +-
 ...orch.nn.modules.activation.LogSigmoid.html |   4 +-
 ...orch.nn.modules.activation.LogSoftmax.html |   6 +-
 .../torch.nn.modules.activation.Mish.html     |   6 +-
 ...modules.activation.MultiheadAttention.html |   6 +-
 .../torch.nn.modules.activation.PReLU.html    |   8 +-
 .../torch.nn.modules.activation.RReLU.html    |   6 +-
 .../torch.nn.modules.activation.ReLU.html     |   6 +-
 .../torch.nn.modules.activation.ReLU6.html    |   4 +-
 .../torch.nn.modules.activation.SELU.html     |   6 +-
 .../torch.nn.modules.activation.SiLU.html     |   6 +-
 .../torch.nn.modules.activation.Sigmoid.html  |   4 +-
 .../torch.nn.modules.activation.Softmax.html  |   6 +-
 ...torch.nn.modules.activation.Softmax2d.html |   4 +-
 .../torch.nn.modules.activation.Softmin.html  |   6 +-
 .../torch.nn.modules.activation.Softplus.html |   6 +-
 ...orch.nn.modules.activation.Softshrink.html |   6 +-
 .../torch.nn.modules.activation.Softsign.html |   4 +-
 .../torch.nn.modules.activation.Tanh.html     |   4 +-
 ...orch.nn.modules.activation.Tanhshrink.html |   4 +-
 ...torch.nn.modules.activation.Threshold.html |   6 +-
 ...s.adaptive.AdaptiveLogSoftmaxWithLoss.html |  10 +-
 ...orch.nn.modules.batchnorm.BatchNorm1d.html |   2 +-
 ...orch.nn.modules.batchnorm.BatchNorm2d.html |   2 +-
 ...orch.nn.modules.batchnorm.BatchNorm3d.html |   2 +-
 ....nn.modules.batchnorm.LazyBatchNorm1d.html |   4 +-
 ....nn.modules.batchnorm.LazyBatchNorm2d.html |   4 +-
 ....nn.modules.batchnorm.LazyBatchNorm3d.html |   4 +-
 ...ch.nn.modules.batchnorm.SyncBatchNorm.html |   6 +-
 ...modules.channelshuffle.ChannelShuffle.html |   6 +-
 ...torch.nn.modules.container.ModuleDict.html |  14 +-
 ...torch.nn.modules.container.ModuleList.html |   8 +-
 ...ch.nn.modules.container.ParameterDict.html |  24 +-
 ...ch.nn.modules.container.ParameterList.html |   8 +-
 ...torch.nn.modules.container.Sequential.html |  12 +-
 .../torch.nn.modules.conv.Conv1d.html         |   2 +-
 .../torch.nn.modules.conv.Conv2d.html         |   2 +-
 .../torch.nn.modules.conv.Conv3d.html         |   2 +-
 ...torch.nn.modules.conv.ConvTranspose1d.html |   2 +-
 ...torch.nn.modules.conv.ConvTranspose2d.html |   4 +-
 ...torch.nn.modules.conv.ConvTranspose3d.html |   2 +-
 .../torch.nn.modules.conv.LazyConv1d.html     |   4 +-
 .../torch.nn.modules.conv.LazyConv2d.html     |   4 +-
 .../torch.nn.modules.conv.LazyConv3d.html     |   4 +-
 ...h.nn.modules.conv.LazyConvTranspose1d.html |   4 +-
 ...h.nn.modules.conv.LazyConvTranspose2d.html |   4 +-
 ...h.nn.modules.conv.LazyConvTranspose3d.html |   4 +-
 ....nn.modules.distance.CosineSimilarity.html |   4 +-
 ....nn.modules.distance.PairwiseDistance.html |   4 +-
 ...torch.nn.modules.dropout.AlphaDropout.html |   4 +-
 .../torch.nn.modules.dropout.Dropout.html     |   4 +-
 .../torch.nn.modules.dropout.Dropout1d.html   |   4 +-
 .../torch.nn.modules.dropout.Dropout2d.html   |   4 +-
 .../torch.nn.modules.dropout.Dropout3d.html   |   4 +-
 ...n.modules.dropout.FeatureAlphaDropout.html |   4 +-
 .../torch.nn.modules.flatten.Flatten.html     |   6 +-
 .../torch.nn.modules.flatten.Unflatten.html   |   6 +-
 2.9/generated/torch.nn.modules.fold.Fold.html |   6 +-
 .../torch.nn.modules.fold.Unfold.html         |   6 +-
 ...n.modules.instancenorm.InstanceNorm1d.html |   2 +-
 ...n.modules.instancenorm.InstanceNorm2d.html |   2 +-
 ...n.modules.instancenorm.InstanceNorm3d.html |   2 +-
 ...dules.instancenorm.LazyInstanceNorm1d.html |   4 +-
 ...dules.instancenorm.LazyInstanceNorm2d.html |   4 +-
 ...dules.instancenorm.LazyInstanceNorm3d.html |   4 +-
 ...torch.nn.modules.lazy.LazyModuleMixin.html |   6 +-
 .../torch.nn.modules.linear.Bilinear.html     |   8 +-
 .../torch.nn.modules.linear.Identity.html     |   4 +-
 .../torch.nn.modules.linear.LazyLinear.html   |   8 +-
 .../torch.nn.modules.linear.Linear.html       |   8 +-
 .../torch.nn.modules.loss.BCELoss.html        |   4 +-
 ...rch.nn.modules.loss.BCEWithLogitsLoss.html |   4 +-
 .../torch.nn.modules.loss.CTCLoss.html        |   4 +-
 ...h.nn.modules.loss.CosineEmbeddingLoss.html |   4 +-
 ...orch.nn.modules.loss.CrossEntropyLoss.html |   4 +-
 ...torch.nn.modules.loss.GaussianNLLLoss.html |   4 +-
 ...ch.nn.modules.loss.HingeEmbeddingLoss.html |   4 +-
 .../torch.nn.modules.loss.HuberLoss.html      |   4 +-
 .../torch.nn.modules.loss.KLDivLoss.html      |   4 +-
 .../torch.nn.modules.loss.L1Loss.html         |   4 +-
 .../torch.nn.modules.loss.MSELoss.html        |   4 +-
 ...rch.nn.modules.loss.MarginRankingLoss.html |   4 +-
 ....nn.modules.loss.MultiLabelMarginLoss.html |   4 +-
 ...modules.loss.MultiLabelSoftMarginLoss.html |   4 +-
 ...torch.nn.modules.loss.MultiMarginLoss.html |   4 +-
 .../torch.nn.modules.loss.NLLLoss.html        |   4 +-
 .../torch.nn.modules.loss.PoissonNLLLoss.html |   4 +-
 .../torch.nn.modules.loss.SmoothL1Loss.html   |   4 +-
 .../torch.nn.modules.loss.SoftMarginLoss.html |   4 +-
 ...rch.nn.modules.loss.TripletMarginLoss.html |   4 +-
 ...es.loss.TripletMarginWithDistanceLoss.html |   4 +-
 ....module.register_module_backward_hook.html |   2 +-
 ...ister_module_buffer_registration_hook.html |   2 +-
 ...s.module.register_module_forward_hook.html |   2 +-
 ...dule.register_module_forward_pre_hook.html |   2 +-
 ...le.register_module_full_backward_hook.html |   2 +-
 ...egister_module_full_backward_pre_hook.html |   2 +-
 ...ister_module_module_registration_hook.html |   2 +-
 ...er_module_parameter_registration_hook.html |   2 +-
 ...ch.nn.modules.normalization.GroupNorm.html |   2 +-
 ...ch.nn.modules.normalization.LayerNorm.html |   2 +-
 ...dules.normalization.LocalResponseNorm.html |   6 +-
 ...orch.nn.modules.normalization.RMSNorm.html |   8 +-
 ...orch.nn.modules.padding.CircularPad1d.html |   2 +-
 ...orch.nn.modules.padding.CircularPad2d.html |   2 +-
 ...orch.nn.modules.padding.CircularPad3d.html |   2 +-
 ...orch.nn.modules.padding.ConstantPad1d.html |   2 +-
 ...orch.nn.modules.padding.ConstantPad2d.html |   2 +-
 ...orch.nn.modules.padding.ConstantPad3d.html |   2 +-
 ...ch.nn.modules.padding.ReflectionPad1d.html |   2 +-
 ...ch.nn.modules.padding.ReflectionPad2d.html |   2 +-
 ...ch.nn.modules.padding.ReflectionPad3d.html |   2 +-
 ...h.nn.modules.padding.ReplicationPad1d.html |   2 +-
 ...h.nn.modules.padding.ReplicationPad2d.html |   2 +-
 ...h.nn.modules.padding.ReplicationPad3d.html |   2 +-
 .../torch.nn.modules.padding.ZeroPad1d.html   |   4 +-
 .../torch.nn.modules.padding.ZeroPad2d.html   |   4 +-
 .../torch.nn.modules.padding.ZeroPad3d.html   |   4 +-
 ....nn.modules.pixelshuffle.PixelShuffle.html |   6 +-
 ...n.modules.pixelshuffle.PixelUnshuffle.html |   6 +-
 ....nn.modules.pooling.AdaptiveAvgPool1d.html |   4 +-
 ....nn.modules.pooling.AdaptiveAvgPool2d.html |   4 +-
 ....nn.modules.pooling.AdaptiveAvgPool3d.html |   4 +-
 ....nn.modules.pooling.AdaptiveMaxPool1d.html |   4 +-
 ....nn.modules.pooling.AdaptiveMaxPool2d.html |   4 +-
 ....nn.modules.pooling.AdaptiveMaxPool3d.html |   4 +-
 .../torch.nn.modules.pooling.AvgPool1d.html   |   4 +-
 .../torch.nn.modules.pooling.AvgPool2d.html   |   4 +-
 .../torch.nn.modules.pooling.AvgPool3d.html   |   4 +-
 ...n.modules.pooling.FractionalMaxPool2d.html |   2 +-
 ...n.modules.pooling.FractionalMaxPool3d.html |   2 +-
 .../torch.nn.modules.pooling.LPPool1d.html    |   4 +-
 .../torch.nn.modules.pooling.LPPool2d.html    |   4 +-
 .../torch.nn.modules.pooling.LPPool3d.html    |   4 +-
 .../torch.nn.modules.pooling.MaxPool1d.html   |   4 +-
 .../torch.nn.modules.pooling.MaxPool2d.html   |   4 +-
 .../torch.nn.modules.pooling.MaxPool3d.html   |   4 +-
 .../torch.nn.modules.pooling.MaxUnpool1d.html |   4 +-
 .../torch.nn.modules.pooling.MaxUnpool2d.html |   4 +-
 .../torch.nn.modules.pooling.MaxUnpool3d.html |   4 +-
 2.9/generated/torch.nn.modules.rnn.GRU.html   |   2 +-
 .../torch.nn.modules.rnn.GRUCell.html         |   2 +-
 2.9/generated/torch.nn.modules.rnn.LSTM.html  |   2 +-
 .../torch.nn.modules.rnn.LSTMCell.html        |   2 +-
 2.9/generated/torch.nn.modules.rnn.RNN.html   |   4 +-
 .../torch.nn.modules.rnn.RNNBase.html         |   4 +-
 .../torch.nn.modules.rnn.RNNCell.html         |   2 +-
 .../torch.nn.modules.sparse.Embedding.html    |   4 +-
 .../torch.nn.modules.sparse.EmbeddingBag.html |   6 +-
 ...ch.nn.modules.transformer.Transformer.html |   6 +-
 ...odules.transformer.TransformerDecoder.html |   4 +-
 ...s.transformer.TransformerDecoderLayer.html |   4 +-
 ...odules.transformer.TransformerEncoder.html |   4 +-
 ...s.transformer.TransformerEncoderLayer.html |   4 +-
 .../torch.nn.modules.upsampling.Upsample.html |   6 +-
 ...dules.upsampling.UpsamplingBilinear2d.html |   2 +-
 ...odules.upsampling.UpsamplingNearest2d.html |   2 +-
 ...h.nn.parallel.DistributedDataParallel.html |  10 +-
 2.9/generated/torch.nn.parameter.Buffer.html  |   2 +-
 .../torch.nn.parameter.Parameter.html         |   2 +-
 ...orch.nn.parameter.UninitializedBuffer.html |   2 +-
 ...h.nn.parameter.UninitializedParameter.html |   4 +-
 2.9/generated/torch.nn.parameter.is_lazy.html |   2 +-
 ...rch.nn.utils.clip_grad.clip_grad_norm.html |   2 +-
 ...ch.nn.utils.clip_grad.clip_grad_norm_.html |   2 +-
 ...h.nn.utils.clip_grad.clip_grad_value_.html |   2 +-
 .../torch.nn.utils.clip_grad_norm.html        |   2 +-
 .../torch.nn.utils.clip_grad_norm_.html       |   2 +-
 .../torch.nn.utils.clip_grad_value_.html      |   2 +-
 .../torch.nn.utils.clip_grads_with_norm_.html |   2 +-
 ...s.convert_conv2d_weight_memory_format.html |   2 +-
 ...s.convert_conv3d_weight_memory_format.html |   2 +-
 ...nvert_parameters.parameters_to_vector.html |   2 +-
 ...nvert_parameters.vector_to_parameters.html |   2 +-
 .../torch.nn.utils.fuse_conv_bn_eval.html     |   2 +-
 .../torch.nn.utils.fuse_conv_bn_weights.html  |   2 +-
 .../torch.nn.utils.fuse_linear_bn_eval.html   |   2 +-
 ...torch.nn.utils.fuse_linear_bn_weights.html |   2 +-
 ...rch.nn.utils.fusion.fuse_conv_bn_eval.html |   2 +-
 ....nn.utils.fusion.fuse_conv_bn_weights.html |   2 +-
 ...h.nn.utils.fusion.fuse_linear_bn_eval.html |   2 +-
 ...n.utils.fusion.fuse_linear_bn_weights.html |   2 +-
 .../torch.nn.utils.get_total_norm.html        |   2 +-
 .../torch.nn.utils.init.skip_init.html        |   2 +-
 ...t.convert_conv2d_weight_memory_format.html |   2 +-
 ...t.convert_conv3d_weight_memory_format.html |   2 +-
 .../torch.nn.utils.parameters_to_vector.html  |   2 +-
 ....nn.utils.parametrizations.orthogonal.html |   2 +-
 ....utils.parametrizations.spectral_norm.html |   2 +-
 ...nn.utils.parametrizations.weight_norm.html |   2 +-
 ...utils.parametrize.ParametrizationList.html |   4 +-
 .../torch.nn.utils.parametrize.cached.html    |   2 +-
 ....nn.utils.parametrize.is_parametrized.html |   2 +-
 ....parametrize.register_parametrization.html |   2 +-
 ...s.parametrize.remove_parametrizations.html |   2 +-
 ....transfer_parametrizations_and_params.html |   2 +-
 ...ametrize.type_before_parametrizations.html |   2 +-
 ...orch.nn.utils.prune.BasePruningMethod.html |  12 +-
 .../torch.nn.utils.prune.CustomFromMask.html  |  10 +-
 .../torch.nn.utils.prune.Identity.html        |  10 +-
 .../torch.nn.utils.prune.L1Unstructured.html  |  10 +-
 .../torch.nn.utils.prune.LnStructured.html    |  12 +-
 ...torch.nn.utils.prune.PruningContainer.html |  14 +-
 ...torch.nn.utils.prune.RandomStructured.html |  12 +-
 ...rch.nn.utils.prune.RandomUnstructured.html |  10 +-
 ...torch.nn.utils.prune.custom_from_mask.html |   2 +-
 ...ch.nn.utils.prune.global_unstructured.html |   2 +-
 .../torch.nn.utils.prune.identity.html        |   2 +-
 .../torch.nn.utils.prune.is_pruned.html       |   2 +-
 .../torch.nn.utils.prune.l1_unstructured.html |   2 +-
 .../torch.nn.utils.prune.ln_structured.html   |   2 +-
 ...orch.nn.utils.prune.random_structured.html |   2 +-
 ...ch.nn.utils.prune.random_unstructured.html |   2 +-
 .../torch.nn.utils.prune.remove.html          |   2 +-
 .../torch.nn.utils.remove_spectral_norm.html  |   2 +-
 .../torch.nn.utils.remove_weight_norm.html    |   2 +-
 .../torch.nn.utils.rnn.PackedSequence.html    |   6 +-
 ...torch.nn.utils.rnn.invert_permutation.html |   2 +-
 ...rch.nn.utils.rnn.pack_padded_sequence.html |   2 +-
 .../torch.nn.utils.rnn.pack_sequence.html     |   2 +-
 ...orch.nn.utils.rnn.pad_packed_sequence.html |   2 +-
 .../torch.nn.utils.rnn.pad_sequence.html      |   2 +-
 .../torch.nn.utils.rnn.unpack_sequence.html   |   2 +-
 .../torch.nn.utils.rnn.unpad_sequence.html    |   2 +-
 2.9/generated/torch.nn.utils.skip_init.html   |   2 +-
 .../torch.nn.utils.spectral_norm.html         |   2 +-
 ...ls.spectral_norm.remove_spectral_norm.html |   2 +-
 ....nn.utils.spectral_norm.spectral_norm.html |   2 +-
 ...ch.nn.utils.stateless.functional_call.html |   2 +-
 .../torch.nn.utils.vector_to_parameters.html  |   2 +-
 2.9/generated/torch.nn.utils.weight_norm.html |   2 +-
 ....utils.weight_norm.remove_weight_norm.html |   2 +-
 ...orch.nn.utils.weight_norm.weight_norm.html |   2 +-
 2.9/generated/torch.no_grad.html              |   2 +-
 2.9/generated/torch.norm.html                 |   2 +-
 2.9/generated/torch.optim.ASGD.html           |  24 +-
 2.9/generated/torch.optim.Adadelta.html       |  24 +-
 2.9/generated/torch.optim.Adafactor.html      |  22 +-
 2.9/generated/torch.optim.Adagrad.html        |  26 +-
 2.9/generated/torch.optim.Adam.html           |  24 +-
 2.9/generated/torch.optim.AdamW.html          |  24 +-
 2.9/generated/torch.optim.Adamax.html         |  24 +-
 2.9/generated/torch.optim.LBFGS.html          |  24 +-
 2.9/generated/torch.optim.Muon.html           |  22 +-
 2.9/generated/torch.optim.NAdam.html          |  24 +-
 ...torch.optim.Optimizer.add_param_group.html |   2 +-
 ...torch.optim.Optimizer.load_state_dict.html |   2 +-
 ...er.register_load_state_dict_post_hook.html |   2 +-
 ...zer.register_load_state_dict_pre_hook.html |   2 +-
 ...timizer.register_state_dict_post_hook.html |   2 +-
 ...ptimizer.register_state_dict_pre_hook.html |   2 +-
 ...tim.Optimizer.register_step_post_hook.html |   2 +-
 ...ptim.Optimizer.register_step_pre_hook.html |   2 +-
 .../torch.optim.Optimizer.state_dict.html     |   2 +-
 2.9/generated/torch.optim.Optimizer.step.html |   2 +-
 .../torch.optim.Optimizer.zero_grad.html      |   2 +-
 2.9/generated/torch.optim.RAdam.html          |  24 +-
 2.9/generated/torch.optim.RMSprop.html        |  24 +-
 2.9/generated/torch.optim.Rprop.html          |  24 +-
 2.9/generated/torch.optim.SGD.html            |  24 +-
 2.9/generated/torch.optim.SparseAdam.html     |  24 +-
 .../torch.optim.adadelta.Adadelta.html        |  24 +-
 .../torch.optim.adadelta.adadelta.html        |   2 +-
 .../torch.optim.adagrad.Adagrad.html          |  26 +-
 .../torch.optim.adagrad.adagrad.html          |   2 +-
 2.9/generated/torch.optim.adam.Adam.html      |  24 +-
 2.9/generated/torch.optim.adam.adam.html      |   2 +-
 2.9/generated/torch.optim.adamax.Adamax.html  |  24 +-
 2.9/generated/torch.optim.adamax.adamax.html  |   2 +-
 2.9/generated/torch.optim.adamw.AdamW.html    |  24 +-
 2.9/generated/torch.optim.adamw.adamw.html    |   2 +-
 2.9/generated/torch.optim.asgd.ASGD.html      |  24 +-
 2.9/generated/torch.optim.asgd.asgd.html      |   2 +-
 2.9/generated/torch.optim.lbfgs.LBFGS.html    |  24 +-
 ...h.optim.lr_scheduler.ChainedScheduler.html |  12 +-
 .../torch.optim.lr_scheduler.ConstantLR.html  |  12 +-
 ....optim.lr_scheduler.CosineAnnealingLR.html |  12 +-
 ...scheduler.CosineAnnealingWarmRestarts.html |  12 +-
 .../torch.optim.lr_scheduler.CyclicLR.html    |  14 +-
 ...orch.optim.lr_scheduler.ExponentialLR.html |  12 +-
 .../torch.optim.lr_scheduler.LRScheduler.html |  12 +-
 .../torch.optim.lr_scheduler.LambdaLR.html    |  12 +-
 .../torch.optim.lr_scheduler.LinearLR.html    |  12 +-
 .../torch.optim.lr_scheduler.MultiStepLR.html |  12 +-
 ...h.optim.lr_scheduler.MultiplicativeLR.html |  12 +-
 .../torch.optim.lr_scheduler.OneCycleLR.html  |  12 +-
 ...torch.optim.lr_scheduler.PolynomialLR.html |  12 +-
 ....optim.lr_scheduler.ReduceLROnPlateau.html |  12 +-
 ...torch.optim.lr_scheduler.SequentialLR.html |  14 +-
 .../torch.optim.lr_scheduler.StepLR.html      |  12 +-
 2.9/generated/torch.optim.nadam.NAdam.html    |  24 +-
 2.9/generated/torch.optim.nadam.nadam.html    |   2 +-
 2.9/generated/torch.optim.radam.RAdam.html    |  24 +-
 2.9/generated/torch.optim.radam.radam.html    |   2 +-
 .../torch.optim.rmsprop.RMSprop.html          |  24 +-
 .../torch.optim.rmsprop.rmsprop.html          |   2 +-
 2.9/generated/torch.optim.rprop.Rprop.html    |  24 +-
 2.9/generated/torch.optim.rprop.rprop.html    |   2 +-
 2.9/generated/torch.optim.sgd.SGD.html        |  24 +-
 2.9/generated/torch.optim.sgd.sgd.html        |   2 +-
 .../torch.optim.sparse_adam.SparseAdam.html   |  24 +-
 .../torch.optim.swa_utils.AveragedModel.html  | 112 ++--
 .../torch.optim.swa_utils.SWALR.html          |  12 +-
 2.9/generated/torch.pca_lowrank.html          |   2 +-
 .../torch.quasirandom.SobolEngine.html        |  10 +-
 2.9/generated/torch.save.html                 |   2 +-
 2.9/generated/torch.seed.html                 |   2 +-
 2.9/generated/torch.set_default_device.html   |   2 +-
 2.9/generated/torch.set_default_dtype.html    |   2 +-
 .../torch.set_default_tensor_type.html        |   2 +-
 .../torch.set_deterministic_debug_mode.html   |   2 +-
 .../torch.set_float32_matmul_precision.html   |   2 +-
 2.9/generated/torch.set_printoptions.html     |   2 +-
 2.9/generated/torch.set_rng_state.html        |   2 +-
 2.9/generated/torch.set_warn_always.html      |   2 +-
 .../torch.signal.windows.bartlett.html        |   2 +-
 .../torch.signal.windows.blackman.html        |   2 +-
 .../torch.signal.windows.cosine.html          |   2 +-
 .../torch.signal.windows.exponential.html     |   2 +-
 .../torch.signal.windows.gaussian.html        |   2 +-
 .../torch.signal.windows.general_cosine.html  |   2 +-
 .../torch.signal.windows.general_hamming.html |   2 +-
 .../torch.signal.windows.hamming.html         |   2 +-
 2.9/generated/torch.signal.windows.hann.html  |   2 +-
 .../torch.signal.windows.kaiser.html          |   2 +-
 .../torch.signal.windows.nuttall.html         |   2 +-
 .../torch.sparse.as_sparse_gradcheck.html     |   2 +-
 ...sparse.check_sparse_tensor_invariants.html |   8 +-
 2.9/generated/torch.sparse.sum.html           |   2 +-
 2.9/generated/torch.split.html                |   2 +-
 2.9/generated/torch.stft.html                 |   2 +-
 2.9/generated/torch.svd_lowrank.html          |   2 +-
 2.9/generated/torch.sym_float.html            |   2 +-
 2.9/generated/torch.sym_fresh_size.html       |   2 +-
 2.9/generated/torch.sym_int.html              |   2 +-
 2.9/generated/torch.sym_ite.html              |   2 +-
 2.9/generated/torch.sym_max.html              |   2 +-
 2.9/generated/torch.sym_min.html              |   2 +-
 2.9/generated/torch.sym_not.html              |   2 +-
 2.9/generated/torch.sym_sum.html              |   2 +-
 2.9/generated/torch.tensordot.html            |   2 +-
 2.9/generated/torch.unique.html               |   2 +-
 2.9/generated/torch.unique_consecutive.html   |   2 +-
 2.9/generated/torch.unravel_index.html        |   2 +-
 .../torch.use_deterministic_algorithms.html   |   2 +-
 ...erate_methods_for_privateuse1_backend.html |   2 +-
 .../torch.utils.get_cpp_backtrace.html        |   2 +-
 ...orch.utils.rename_privateuse1_backend.html |   2 +-
 2.9/generated/torch.utils.set_module.html     |   2 +-
 2.9/generated/torch.utils.swap_tensors.html   |   2 +-
 2.9/generated/torch.vmap.html                 |   2 +-
 2.9/generated/torch.xpu.Event.html            |  12 +-
 2.9/generated/torch.xpu.Stream.html           |  12 +-
 2.9/generated/torch.xpu.StreamContext.html    |   2 +-
 2.9/generated/torch.xpu.current_device.html   |   2 +-
 2.9/generated/torch.xpu.current_stream.html   |   2 +-
 2.9/generated/torch.xpu.device.html           |   2 +-
 2.9/generated/torch.xpu.device_count.html     |   2 +-
 2.9/generated/torch.xpu.device_of.html        |   2 +-
 2.9/generated/torch.xpu.get_arch_list.html    |   2 +-
 .../torch.xpu.get_device_capability.html      |   2 +-
 2.9/generated/torch.xpu.get_device_name.html  |   2 +-
 .../torch.xpu.get_device_properties.html      |   2 +-
 .../torch.xpu.get_gencode_flags.html          |   2 +-
 2.9/generated/torch.xpu.get_rng_state.html    |   2 +-
 .../torch.xpu.get_rng_state_all.html          |   2 +-
 .../torch.xpu.get_stream_from_external.html   |   2 +-
 2.9/generated/torch.xpu.init.html             |   2 +-
 2.9/generated/torch.xpu.initial_seed.html     |   2 +-
 2.9/generated/torch.xpu.is_available.html     |   2 +-
 2.9/generated/torch.xpu.is_initialized.html   |   2 +-
 2.9/generated/torch.xpu.manual_seed.html      |   2 +-
 2.9/generated/torch.xpu.manual_seed_all.html  |   2 +-
 .../torch.xpu.memory.empty_cache.html         |   2 +-
 ...torch.xpu.memory.max_memory_allocated.html |   2 +-
 .../torch.xpu.memory.max_memory_reserved.html |   2 +-
 .../torch.xpu.memory.mem_get_info.html        |   2 +-
 .../torch.xpu.memory.memory_allocated.html    |   2 +-
 .../torch.xpu.memory.memory_reserved.html     |   2 +-
 .../torch.xpu.memory.memory_stats.html        |   2 +-
 ...pu.memory.memory_stats_as_nested_dict.html |   2 +-
 ...memory.reset_accumulated_memory_stats.html |   2 +-
 ...ch.xpu.memory.reset_peak_memory_stats.html |   2 +-
 2.9/generated/torch.xpu.seed.html             |   2 +-
 2.9/generated/torch.xpu.seed_all.html         |   2 +-
 2.9/generated/torch.xpu.set_device.html       |   2 +-
 2.9/generated/torch.xpu.set_rng_state.html    |   2 +-
 .../torch.xpu.set_rng_state_all.html          |   2 +-
 2.9/generated/torch.xpu.set_stream.html       |   2 +-
 2.9/generated/torch.xpu.stream.html           |   2 +-
 2.9/generated/torch.xpu.synchronize.html      |   2 +-
 2.9/hub.html                                  |  14 +-
 2.9/library.html                              |  46 +-
 2.9/mobile_optimizer.html                     |   2 +-
 2.9/model_zoo.html                            |   2 +-
 2.9/module_tracker.html                       |   2 +-
 2.9/monitor.html                              |   4 +-
 2.9/multiprocessing.html                      |  12 +-
 2.9/named_tensor.html                         |   8 +-
 2.9/nested.html                               |  10 +-
 2.9/nn.attention.flex_attention.html          |  36 +-
 2.9/nn.init.html                              |  30 +-
 2.9/notes/serialization.html                  |  26 +-
 2.9/onnx.html                                 |  10 +-
 2.9/onnx_export.html                          |  18 +-
 2.9/onnx_ops.html                             |  10 +-
 2.9/onnx_verification.html                    |   6 +-
 2.9/optim.html                                |   6 +-
 2.9/package.html                              |  76 +--
 2.9/profiler.html                             |  42 +-
 2.9/quantization.html                         |   6 +-
 2.9/random.html                               |  12 +-
 2.9/rpc.html                                  |  28 +-
 2.9/storage.html                              | 180 +++---
 2.9/tensorboard.html                          |  38 +-
 2.9/testing.html                              |   6 +-
 2.9/torch.compiler_aot_inductor.html          |   4 +-
 2.9/torch.html                                |  16 +-
 2.9/torch.overrides.html                      |  16 +-
 2.9/torch_cuda_memory.html                    |   6 +-
 replace_github_links.sh                       |   9 +-
 1256 files changed, 3747 insertions(+), 3748 deletions(-)

diff --git a/2.9/amp.html b/2.9/amp.html
index 9c69740ae1f..48f699d237c 100644
--- a/2.9/amp.html
+++ b/2.9/amp.html
@@ -4448,7 +4448,7 @@ <h1>Automatic Mixed Precision package - torch.amp<a class="headerlink" href="#au
 <span id="id1"></span><h2><a class="toc-backref" href="#id4">Autocasting</a><a class="headerlink" href="#autocasting" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.amp.autocast_mode.is_autocast_available">
-<span class="sig-prename descclassname"><span class="pre">torch.amp.autocast_mode.</span></span><span class="sig-name descname"><span class="pre">is_autocast_available</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/amp/autocast_mode.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.amp.autocast_mode.is_autocast_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.amp.autocast_mode.</span></span><span class="sig-name descname"><span class="pre">is_autocast_available</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/amp/autocast_mode.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.amp.autocast_mode.is_autocast_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a bool indicating if autocast is available on <code class="xref py py-attr docutils literal notranslate"><span class="pre">device_type</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4464,7 +4464,7 @@ <h1>Automatic Mixed Precision package - torch.amp<a class="headerlink" href="#au
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autocast">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">autocast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/amp/autocast_mode.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autocast" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">autocast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/amp/autocast_mode.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autocast" title="Permalink to this definition">#</a></dt>
 <dd><p>Instances of <a class="reference internal" href="#torch.autocast" title="torch.autocast"><code class="xref py py-class docutils literal notranslate"><span class="pre">autocast</span></code></a> serve as context managers or decorators that
 allow regions of your script to run in mixed precision.</p>
 <p>In these regions, ops run in an op-specific dtype chosen by autocast
@@ -4632,7 +4632,7 @@ <h1>Automatic Mixed Precision package - torch.amp<a class="headerlink" href="#au
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.amp.custom_fwd">
-<span class="sig-prename descclassname"><span class="pre">torch.amp.</span></span><span class="sig-name descname"><span class="pre">custom_fwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fwd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/amp/autocast_mode.py#L487"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.amp.custom_fwd" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.amp.</span></span><span class="sig-name descname"><span class="pre">custom_fwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fwd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/amp/autocast_mode.py#L487"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.amp.custom_fwd" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a helper decorator for <code class="docutils literal notranslate"><span class="pre">forward</span></code> methods of custom autograd functions.</p>
 <p>Autograd functions are subclasses of <a class="reference internal" href="autograd.html#torch.autograd.Function" title="torch.autograd.Function"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.autograd.Function</span></code></a>.
 See the <a class="reference internal" href="notes/amp_examples.html#amp-custom-examples"><span class="std std-ref">example page</span></a> for more detail.</p>
@@ -4659,7 +4659,7 @@ <h1>Automatic Mixed Precision package - torch.amp<a class="headerlink" href="#au
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.amp.custom_bwd">
-<span class="sig-prename descclassname"><span class="pre">torch.amp.</span></span><span class="sig-name descname"><span class="pre">custom_bwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">bwd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/amp/autocast_mode.py#L546"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.amp.custom_bwd" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.amp.</span></span><span class="sig-name descname"><span class="pre">custom_bwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">bwd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/amp/autocast_mode.py#L546"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.amp.custom_bwd" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a helper decorator for backward methods of custom autograd functions.</p>
 <p>Autograd functions are subclasses of <a class="reference internal" href="autograd.html#torch.autograd.Function" title="torch.autograd.Function"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.autograd.Function</span></code></a>.
 Ensures that <code class="docutils literal notranslate"><span class="pre">backward</span></code> executes with the same autocast state as <code class="docutils literal notranslate"><span class="pre">forward</span></code>.
@@ -4675,7 +4675,7 @@ <h1>Automatic Mixed Precision package - torch.amp<a class="headerlink" href="#au
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.amp.autocast">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.amp.</span></span><span class="sig-name descname"><span class="pre">autocast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.float16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/amp/autocast_mode.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.amp.autocast" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.amp.</span></span><span class="sig-name descname"><span class="pre">autocast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.float16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/amp/autocast_mode.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.amp.autocast" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="#torch.autocast" title="torch.autocast"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.autocast</span></code></a>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">torch.cuda.amp.autocast(args...)</span></code> is deprecated. Please use <code class="docutils literal notranslate"><span class="pre">torch.amp.autocast(&quot;cuda&quot;,</span> <span class="pre">args...)</span></code> instead.</p>
 <dl class="field-list simple">
@@ -4684,21 +4684,21 @@ <h1>Automatic Mixed Precision package - torch.amp<a class="headerlink" href="#au
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.amp.custom_fwd">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.amp.</span></span><span class="sig-name descname"><span class="pre">custom_fwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fwd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/amp/autocast_mode.py#L65"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.amp.custom_fwd" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.amp.</span></span><span class="sig-name descname"><span class="pre">custom_fwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fwd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/amp/autocast_mode.py#L65"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.amp.custom_fwd" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">torch.cuda.amp.custom_fwd(args...)</span></code> is deprecated. Please use
 <code class="docutils literal notranslate"><span class="pre">torch.amp.custom_fwd(args...,</span> <span class="pre">device_type='cuda')</span></code> instead.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.amp.custom_bwd">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.amp.</span></span><span class="sig-name descname"><span class="pre">custom_bwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">bwd</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/amp/autocast_mode.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.amp.custom_bwd" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.amp.</span></span><span class="sig-name descname"><span class="pre">custom_bwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">bwd</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/amp/autocast_mode.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.amp.custom_bwd" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">torch.cuda.amp.custom_bwd(args...)</span></code> is deprecated. Please use
 <code class="docutils literal notranslate"><span class="pre">torch.amp.custom_bwd(args...,</span> <span class="pre">device_type='cuda')</span></code> instead.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cpu.amp.autocast">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cpu.amp.</span></span><span class="sig-name descname"><span class="pre">autocast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.bfloat16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/amp/autocast_mode.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.amp.autocast" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cpu.amp.</span></span><span class="sig-name descname"><span class="pre">autocast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.bfloat16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/amp/autocast_mode.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.amp.autocast" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="#torch.autocast" title="torch.autocast"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.autocast</span></code></a>.
 <code class="docutils literal notranslate"><span class="pre">torch.cpu.amp.autocast(args...)</span></code> is deprecated. Please use <code class="docutils literal notranslate"><span class="pre">torch.amp.autocast(&quot;cpu&quot;,</span> <span class="pre">args...)</span></code> instead.</p>
 <dl class="field-list simple">
@@ -4729,7 +4729,7 @@ <h1>Automatic Mixed Precision package - torch.amp<a class="headerlink" href="#au
 </div>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.amp.GradScaler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.amp.</span></span><span class="sig-name descname"><span class="pre">GradScaler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">init_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">65536.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backoff_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/amp/grad_scaler.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.amp.GradScaler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.amp.</span></span><span class="sig-name descname"><span class="pre">GradScaler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">init_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">65536.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backoff_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/amp/grad_scaler.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.amp.GradScaler" title="Permalink to this definition">#</a></dt>
 <dd><p>See <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.amp.GradScaler</span></code>.
 <code class="docutils literal notranslate"><span class="pre">torch.cuda.amp.GradScaler(args...)</span></code> is deprecated. Please use <code class="docutils literal notranslate"><span class="pre">torch.amp.GradScaler(&quot;cuda&quot;,</span> <span class="pre">args...)</span></code> instead.</p>
 <dl class="field-list simple">
@@ -4738,7 +4738,7 @@ <h1>Automatic Mixed Precision package - torch.amp<a class="headerlink" href="#au
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cpu.amp.GradScaler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cpu.amp.</span></span><span class="sig-name descname"><span class="pre">GradScaler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">init_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">65536.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backoff_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/amp/grad_scaler.py#L9"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.amp.GradScaler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cpu.amp.</span></span><span class="sig-name descname"><span class="pre">GradScaler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">init_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">65536.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backoff_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">growth_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/amp/grad_scaler.py#L9"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.amp.GradScaler" title="Permalink to this definition">#</a></dt>
 <dd><p>See <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.amp.GradScaler</span></code>.
 <code class="docutils literal notranslate"><span class="pre">torch.cpu.amp.GradScaler(args...)</span></code> is deprecated. Please use <code class="docutils literal notranslate"><span class="pre">torch.amp.GradScaler(&quot;cpu&quot;,</span> <span class="pre">args...)</span></code> instead.</p>
 <dl class="field-list simple">
diff --git a/2.9/autograd.html b/2.9/autograd.html
index 05fb3a8eeff..e23293911a9 100644
--- a/2.9/autograd.html
+++ b/2.9/autograd.html
@@ -4629,7 +4629,7 @@ <h2>Tensor autograd functions<a class="headerlink" href="#tensor-autograd-functi
 <h2><span class="hidden-section">Function</span><a class="headerlink" href="#function" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.Function">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">Function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">Function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class to create custom <cite>autograd.Function</cite>.</p>
 <p>To create a custom <cite>autograd.Function</cite>, subclass this class and implement
 the <a class="reference internal" href="generated/torch.autograd.Function.forward.html#torch.autograd.Function.forward" title="torch.autograd.Function.forward"><code class="xref py py-meth docutils literal notranslate"><span class="pre">forward()</span></code></a> and <a class="reference internal" href="generated/torch.autograd.backward.html#torch.autograd.backward" title="torch.autograd.backward"><code class="xref py py-meth docutils literal notranslate"><span class="pre">backward()</span></code></a> static methods. Then, to use your custom
@@ -4772,7 +4772,7 @@ <h2>Profiler<a class="headerlink" href="#profiler" title="Permalink to this head
 <a class="reference internal" href="#torch.autograd.profiler.emit_itt" title="torch.autograd.profiler.emit_itt"><code class="xref py py-class docutils literal notranslate"><span class="pre">emit_itt</span></code></a>.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler.profile">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">profile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_cuda</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_flops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_stack</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_kineto</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">experimental_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">acc_events</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_trace_id_callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.profile" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">profile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_cuda</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_flops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_stack</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_kineto</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">experimental_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">acc_events</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_trace_id_callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.profile" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager that manages autograd profiler state and holds a summary of results.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4907,7 +4907,7 @@ <h2>Profiler<a class="headerlink" href="#profiler" title="Permalink to this head
 </div>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler.emit_nvtx">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">emit_nvtx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L921"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.emit_nvtx" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">emit_nvtx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L921"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.emit_nvtx" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager that makes every autograd operation emit an NVTX range.</p>
 <p>It is useful when running the program under nvprof:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">nvprof</span> <span class="o">--</span><span class="n">profile</span><span class="o">-</span><span class="n">from</span><span class="o">-</span><span class="n">start</span> <span class="n">off</span> <span class="o">-</span><span class="n">o</span> <span class="n">trace_name</span><span class="o">.</span><span class="n">prof</span> <span class="o">--</span> <span class="o">&lt;</span><span class="n">regular</span> <span class="n">command</span> <span class="n">here</span><span class="o">&gt;</span>
@@ -4976,7 +4976,7 @@ <h2>Profiler<a class="headerlink" href="#profiler" title="Permalink to this head
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler.emit_itt">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">emit_itt</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L850"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.emit_itt" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">emit_itt</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L850"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.emit_itt" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager that makes every autograd operation emit an ITT range.</p>
 <p>It is useful when running the program under Intel(R) VTune Profiler:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">vtune</span> <span class="o">&lt;--</span><span class="n">vtune</span><span class="o">-</span><span class="n">flags</span><span class="o">&gt;</span> <span class="o">&lt;</span><span class="n">regular</span> <span class="n">command</span> <span class="n">here</span><span class="o">&gt;</span>
@@ -5027,7 +5027,7 @@ <h2>Profiler<a class="headerlink" href="#profiler" title="Permalink to this head
 <h2>Debugging and anomaly detection<a class="headerlink" href="#debugging-and-anomaly-detection" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.detect_anomaly">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">detect_anomaly</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">check_nan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/anomaly_mode.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.detect_anomaly" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">detect_anomaly</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">check_nan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/anomaly_mode.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.detect_anomaly" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that enable anomaly detection for the autograd engine.</p>
 <p>This does two things:</p>
 <ul class="simple">
@@ -5098,7 +5098,7 @@ <h2>Debugging and anomaly detection<a class="headerlink" href="#debugging-and-an
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.set_detect_anomaly">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">set_detect_anomaly</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_nan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/anomaly_mode.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.set_detect_anomaly" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">set_detect_anomaly</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_nan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/anomaly_mode.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.set_detect_anomaly" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that sets the anomaly detection for the autograd engine on or off.</p>
 <p><code class="docutils literal notranslate"><span class="pre">set_detect_anomaly</span></code> will enable or disable the autograd anomaly detection
 based on its argument <code class="xref py py-attr docutils literal notranslate"><span class="pre">mode</span></code>.
@@ -5184,7 +5184,7 @@ <h2>Autograd graph<a class="headerlink" href="#autograd-graph" title="Permalink
 Also see <a class="reference internal" href="notes/autograd.html#saved-tensors-hooks-doc"><span class="std std-ref">Hooks for saved tensors</span></a>.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.graph.saved_tensors_hooks">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">saved_tensors_hooks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pack_hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unpack_hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L250"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.saved_tensors_hooks" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">saved_tensors_hooks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pack_hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unpack_hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L250"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.saved_tensors_hooks" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that sets a pair of pack / unpack hooks for saved tensors.</p>
 <p>Use this context-manager to define how intermediary results of an operation
 should be packed before saving, and unpacked on retrieval.</p>
@@ -5251,7 +5251,7 @@ <h2>Autograd graph<a class="headerlink" href="#autograd-graph" title="Permalink
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.graph.save_on_cpu">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">save_on_cpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pin_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.save_on_cpu" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">save_on_cpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pin_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.save_on_cpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager under which tensors saved by the forward pass will be stored on cpu, then retrieved for backward.</p>
 <p>When performing operations within this context manager, intermediary
 results saved in the graph during the forward pass will be moved to CPU,
@@ -5291,7 +5291,7 @@ <h2>Autograd graph<a class="headerlink" href="#autograd-graph" title="Permalink
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.graph.disable_saved_tensors_hooks">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">disable_saved_tensors_hooks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">error_message</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.disable_saved_tensors_hooks" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">disable_saved_tensors_hooks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">error_message</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.disable_saved_tensors_hooks" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that disables the saved tensors default hooks feature.</p>
 <p>Useful for if you are creating a feature that does not work with saved
 tensors default hooks.</p>
@@ -5317,7 +5317,7 @@ <h2>Autograd graph<a class="headerlink" href="#autograd-graph" title="Permalink
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.graph.register_multi_grad_hook">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">register_multi_grad_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L450"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.register_multi_grad_hook" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">register_multi_grad_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L450"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.register_multi_grad_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a multi-grad backward hook.</p>
 <p>There are two supported modes: <code class="docutils literal notranslate"><span class="pre">&quot;all&quot;</span></code> and <code class="docutils literal notranslate"><span class="pre">&quot;any&quot;</span></code>.</p>
 <p>Under the <code class="docutils literal notranslate"><span class="pre">&quot;all&quot;</span></code> mode, the hook will be called after gradients with respect to every tensor in
@@ -5368,7 +5368,7 @@ <h2>Autograd graph<a class="headerlink" href="#autograd-graph" title="Permalink
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.graph.allow_mutation_on_saved_tensors">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">allow_mutation_on_saved_tensors</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L734"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.allow_mutation_on_saved_tensors" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">allow_mutation_on_saved_tensors</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L734"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.allow_mutation_on_saved_tensors" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager under which mutating tensors saved for backward is allowed.</p>
 <p>Under this context manager, tensors saved for backward are cloned on mutation,
 so the original version can still be used during backward. Normally, mutating a tensor
@@ -5404,7 +5404,7 @@ <h2>Autograd graph<a class="headerlink" href="#autograd-graph" title="Permalink
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.graph.GradientEdge">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">GradientEdge</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_nr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ownership_token</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.GradientEdge" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">GradientEdge</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_nr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ownership_token</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.GradientEdge" title="Permalink to this definition">#</a></dt>
 <dd><p>Object representing a given gradient edge within the autograd graph.</p>
 <p>To get the gradient edge where a given Tensor gradient will be computed,
 you can do <code class="docutils literal notranslate"><span class="pre">edge</span> <span class="pre">=</span> <span class="pre">autograd.graph.get_gradient_edge(tensor)</span></code>.</p>
@@ -5414,7 +5414,7 @@ <h2>Autograd graph<a class="headerlink" href="#autograd-graph" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.graph.get_gradient_edge">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">get_gradient_edge</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L202"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.get_gradient_edge" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">get_gradient_edge</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L202"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.get_gradient_edge" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the gradient edge for computing the gradient of the given Tensor.</p>
 <p>In particular, it is equivalent to call
 <code class="docutils literal notranslate"><span class="pre">g</span> <span class="pre">=</span> <span class="pre">autograd.grad(loss,</span> <span class="pre">input)</span></code> and <code class="docutils literal notranslate"><span class="pre">g</span> <span class="pre">=</span> <span class="pre">autograd.grad(loss,</span> <span class="pre">get_gradient_edge(input))</span></code>.</p>
diff --git a/2.9/backends.html b/2.9/backends.html
index 165e4a1d583..60b84c60e45 100644
--- a/2.9/backends.html
+++ b/2.9/backends.html
@@ -4414,7 +4414,7 @@
 <span id="torch-backends-cpu"></span><h2>torch.backends.cpu<a class="headerlink" href="#module-torch.backends.cpu" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cpu.get_cpu_capability">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cpu.</span></span><span class="sig-name descname"><span class="pre">get_cpu_capability</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cpu/__init__.py#L9"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cpu.get_cpu_capability" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cpu.</span></span><span class="sig-name descname"><span class="pre">get_cpu_capability</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cpu/__init__.py#L9"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cpu.get_cpu_capability" title="Permalink to this definition">#</a></dt>
 <dd><p>Return cpu capability as a string value.</p>
 <p>Possible values:
 - “DEFAULT”
@@ -4436,7 +4436,7 @@
 <span id="torch-backends-cuda"></span><h2>torch.backends.cuda<a class="headerlink" href="#module-torch.backends.cuda" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.is_built">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">is_built</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.is_built" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">is_built</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.is_built" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether PyTorch is built with CUDA support.</p>
 <p>Note that this doesn’t necessarily mean CUDA is available; just that if this PyTorch
 binary were run on a machine with working CUDA drivers and devices, we would be able to use it.</p>
@@ -4488,7 +4488,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.preferred_blas_library">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">preferred_blas_library</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L235"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.preferred_blas_library" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">preferred_blas_library</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L235"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.preferred_blas_library" title="Permalink to this definition">#</a></dt>
 <dd><p>Override the library PyTorch uses for BLAS operations. Choose between cuBLAS, cuBLASLt, and CK [ROCm-only].</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -4521,7 +4521,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.preferred_rocm_fa_library">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">preferred_rocm_fa_library</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L290"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.preferred_rocm_fa_library" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">preferred_rocm_fa_library</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L290"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.preferred_rocm_fa_library" title="Permalink to this definition">#</a></dt>
 <dd><p>[ROCm-only]
 Override the backend PyTorch uses in ROCm environments for Flash Attention. Choose between AOTriton and CK</p>
 <div class="admonition warning">
@@ -4551,7 +4551,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.preferred_linalg_library">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">preferred_linalg_library</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.preferred_linalg_library" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">preferred_linalg_library</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.preferred_linalg_library" title="Permalink to this definition">#</a></dt>
 <dd><p>Override the heuristic PyTorch uses to choose between cuSOLVER and MAGMA for CUDA linear algebra operations.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -4606,7 +4606,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.flash_sdp_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">flash_sdp_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L335"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.flash_sdp_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">flash_sdp_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L335"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.flash_sdp_enabled" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4616,7 +4616,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.enable_mem_efficient_sdp">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">enable_mem_efficient_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.enable_mem_efficient_sdp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">enable_mem_efficient_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.enable_mem_efficient_sdp" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4628,7 +4628,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.mem_efficient_sdp_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">mem_efficient_sdp_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.mem_efficient_sdp_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">mem_efficient_sdp_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.mem_efficient_sdp_enabled" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4638,7 +4638,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.enable_flash_sdp">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">enable_flash_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L344"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.enable_flash_sdp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">enable_flash_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L344"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.enable_flash_sdp" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4650,7 +4650,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.math_sdp_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">math_sdp_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L371"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.math_sdp_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">math_sdp_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L371"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.math_sdp_enabled" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4660,7 +4660,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.enable_math_sdp">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">enable_math_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.enable_math_sdp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">enable_math_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.enable_math_sdp" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4672,7 +4672,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.fp16_bf16_reduction_math_sdp_allowed">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">fp16_bf16_reduction_math_sdp_allowed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L398"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.fp16_bf16_reduction_math_sdp_allowed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">fp16_bf16_reduction_math_sdp_allowed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L398"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.fp16_bf16_reduction_math_sdp_allowed" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4682,7 +4682,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.allow_fp16_bf16_reduction_math_sdp">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">allow_fp16_bf16_reduction_math_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.allow_fp16_bf16_reduction_math_sdp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">allow_fp16_bf16_reduction_math_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.allow_fp16_bf16_reduction_math_sdp" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4694,7 +4694,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.cudnn_sdp_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">cudnn_sdp_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L480"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.cudnn_sdp_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">cudnn_sdp_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L480"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.cudnn_sdp_enabled" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4704,7 +4704,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.enable_cudnn_sdp">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">enable_cudnn_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L489"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.enable_cudnn_sdp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">enable_cudnn_sdp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L489"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.enable_cudnn_sdp" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4716,7 +4716,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.is_flash_attention_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">is_flash_attention_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L407"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.is_flash_attention_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">is_flash_attention_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L407"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.is_flash_attention_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if PyTorch was built with FlashAttention for scaled_dot_product_attention.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4735,7 +4735,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.can_use_flash_attention">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">can_use_flash_attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L420"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.can_use_flash_attention" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">can_use_flash_attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L420"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.can_use_flash_attention" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if FlashAttention can be utilized in scaled_dot_product_attention.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4763,7 +4763,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.can_use_efficient_attention">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">can_use_efficient_attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L440"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.can_use_efficient_attention" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">can_use_efficient_attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L440"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.can_use_efficient_attention" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if efficient_attention can be utilized in scaled_dot_product_attention.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4791,7 +4791,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.can_use_cudnn_attention">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">can_use_cudnn_attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L460"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.can_use_cudnn_attention" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">can_use_cudnn_attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L460"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.can_use_cudnn_attention" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if cudnn_attention can be utilized in scaled_dot_product_attention.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4819,7 +4819,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cuda.sdp_kernel">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">sdp_kernel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable_flash</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_math</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_mem_efficient</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_cudnn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cuda/__init__.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.sdp_kernel" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cuda.</span></span><span class="sig-name descname"><span class="pre">sdp_kernel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable_flash</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_math</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_mem_efficient</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_cudnn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cuda/__init__.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cuda.sdp_kernel" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This flag is beta and subject to change.</p>
@@ -4835,13 +4835,13 @@
 <span id="torch-backends-cudnn"></span><h2>torch.backends.cudnn<a class="headerlink" href="#module-torch.backends.cudnn" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cudnn.version">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cudnn.</span></span><span class="sig-name descname"><span class="pre">version</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cudnn/__init__.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cudnn.version" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cudnn.</span></span><span class="sig-name descname"><span class="pre">version</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cudnn/__init__.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cudnn.version" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the version of cuDNN.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cudnn.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cudnn.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cudnn/__init__.py#L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cudnn.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cudnn.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cudnn/__init__.py#L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cudnn.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a bool indicating if CUDNN is currently available.</p>
 </dd></dl>
 
@@ -4887,7 +4887,7 @@
 <span id="torch-backends-cusparselt"></span><h2>torch.backends.cusparselt<a class="headerlink" href="#module-torch.backends.cusparselt" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cusparselt.version">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cusparselt.</span></span><span class="sig-name descname"><span class="pre">version</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cusparselt/__init__.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cusparselt.version" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cusparselt.</span></span><span class="sig-name descname"><span class="pre">version</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cusparselt/__init__.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cusparselt.version" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the version of cuSPARSELt</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4898,7 +4898,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.cusparselt.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.cusparselt.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/cusparselt/__init__.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cusparselt.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.cusparselt.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/cusparselt/__init__.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.cusparselt.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a bool indicating if cuSPARSELt is currently available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4912,7 +4912,7 @@
 <span id="torch-backends-mha"></span><h2>torch.backends.mha<a class="headerlink" href="#module-torch.backends.mha" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.mha.get_fastpath_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.mha.</span></span><span class="sig-name descname"><span class="pre">get_fastpath_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/mha/__init__.py#L9"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mha.get_fastpath_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.mha.</span></span><span class="sig-name descname"><span class="pre">get_fastpath_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/mha/__init__.py#L9"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mha.get_fastpath_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether fast path for TransformerEncoder and MultiHeadAttention
 is enabled, or <code class="docutils literal notranslate"><span class="pre">True</span></code> if jit is scripting.</p>
 <div class="admonition note">
@@ -4929,7 +4929,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.mha.set_fastpath_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.mha.</span></span><span class="sig-name descname"><span class="pre">set_fastpath_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/mha/__init__.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mha.set_fastpath_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.mha.</span></span><span class="sig-name descname"><span class="pre">set_fastpath_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/mha/__init__.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mha.set_fastpath_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether fast path is enabled</p>
 <dl class="field-list simple">
 </dl>
@@ -4950,7 +4950,7 @@
 <span id="torch-backends-mps"></span><h2>torch.backends.mps<a class="headerlink" href="#module-torch.backends.mps" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.mps.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.mps.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/mps/__init__.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mps.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.mps.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/mps/__init__.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mps.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a bool indicating if MPS is currently available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4961,7 +4961,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.mps.is_built">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.mps.</span></span><span class="sig-name descname"><span class="pre">is_built</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/mps/__init__.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mps.is_built" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.mps.</span></span><span class="sig-name descname"><span class="pre">is_built</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/mps/__init__.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mps.is_built" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether PyTorch is built with MPS support.</p>
 <p>Note that this doesn’t necessarily mean MPS is available; just that
 if this PyTorch binary were run a machine with working MPS drivers
@@ -4978,13 +4978,13 @@
 <span id="torch-backends-mkl"></span><h2>torch.backends.mkl<a class="headerlink" href="#module-torch.backends.mkl" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.mkl.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.mkl.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/mkl/__init__.py#L5"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mkl.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.mkl.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/mkl/__init__.py#L5"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mkl.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether PyTorch is built with MKL support.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.backends.mkl.verbose">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.backends.mkl.</span></span><span class="sig-name descname"><span class="pre">verbose</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/mkl/__init__.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mkl.verbose" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.backends.mkl.</span></span><span class="sig-name descname"><span class="pre">verbose</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/mkl/__init__.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mkl.verbose" title="Permalink to this definition">#</a></dt>
 <dd><p>On-demand oneMKL verbosing functionality.</p>
 <p>To make it easier to debug performance issues, oneMKL can dump verbose
 messages containing execution information like duration while executing
@@ -5017,12 +5017,12 @@
 <span id="torch-backends-mkldnn"></span><h2>torch.backends.mkldnn<a class="headerlink" href="#module-torch.backends.mkldnn" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.mkldnn.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.mkldnn.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/mkldnn/__init__.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mkldnn.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.mkldnn.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/mkldnn/__init__.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mkldnn.is_available" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.backends.mkldnn.verbose">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.backends.mkldnn.</span></span><span class="sig-name descname"><span class="pre">verbose</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">level</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/mkldnn/__init__.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mkldnn.verbose" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.backends.mkldnn.</span></span><span class="sig-name descname"><span class="pre">verbose</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">level</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/mkldnn/__init__.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.mkldnn.verbose" title="Permalink to this definition">#</a></dt>
 <dd><p>On-demand oneDNN (former MKL-DNN) verbosing functionality.</p>
 <p>To make it easier to debug performance issues, oneDNN can dump verbose
 messages containing information like kernel size, input data size and
@@ -5056,19 +5056,19 @@
 <span id="torch-backends-nnpack"></span><h2>torch.backends.nnpack<a class="headerlink" href="#module-torch.backends.nnpack" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.nnpack.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.nnpack.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/nnpack/__init__.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.nnpack.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.nnpack.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/nnpack/__init__.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.nnpack.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether PyTorch is built with NNPACK support.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.nnpack.flags">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.nnpack.</span></span><span class="sig-name descname"><span class="pre">flags</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/nnpack/__init__.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.nnpack.flags" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.nnpack.</span></span><span class="sig-name descname"><span class="pre">flags</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/nnpack/__init__.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.nnpack.flags" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager for setting if nnpack is enabled globally</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.nnpack.set_flags">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.nnpack.</span></span><span class="sig-name descname"><span class="pre">set_flags</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">_enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/nnpack/__init__.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.nnpack.set_flags" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.nnpack.</span></span><span class="sig-name descname"><span class="pre">set_flags</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">_enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/nnpack/__init__.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.nnpack.set_flags" title="Permalink to this definition">#</a></dt>
 <dd><p>Set if nnpack is enabled globally</p>
 </dd></dl>
 
@@ -5077,7 +5077,7 @@
 <span id="torch-backends-openmp"></span><h2>torch.backends.openmp<a class="headerlink" href="#module-torch.backends.openmp" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.openmp.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.openmp.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/openmp/__init__.py#L5"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.openmp.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.openmp.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/openmp/__init__.py#L5"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.openmp.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether PyTorch is built with OpenMP support.</p>
 </dd></dl>
 
@@ -5086,7 +5086,7 @@
 <span id="torch-backends-opt-einsum"></span><h2>torch.backends.opt_einsum<a class="headerlink" href="#module-torch.backends.opt_einsum" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.opt_einsum.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.opt_einsum.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/opt_einsum/__init__.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.opt_einsum.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.opt_einsum.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/opt_einsum/__init__.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.opt_einsum.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a bool indicating if opt_einsum is currently available.</p>
 <p>You must install opt-einsum in order for torch to automatically optimize einsum. To
 make opt-einsum available, you can install it along with torch: <code class="docutils literal notranslate"><span class="pre">pip</span> <span class="pre">install</span> <span class="pre">torch[opt-einsum]</span></code>
@@ -5102,7 +5102,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.backends.opt_einsum.get_opt_einsum">
-<span class="sig-prename descclassname"><span class="pre">torch.backends.opt_einsum.</span></span><span class="sig-name descname"><span class="pre">get_opt_einsum</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/backends/opt_einsum/__init__.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.opt_einsum.get_opt_einsum" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.backends.opt_einsum.</span></span><span class="sig-name descname"><span class="pre">get_opt_einsum</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/backends/opt_einsum/__init__.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.backends.opt_einsum.get_opt_einsum" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the opt_einsum package if opt_einsum is currently available, else None.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/benchmark_utils.html b/2.9/benchmark_utils.html
index 7be1a72b03d..ff49ed1613b 100644
--- a/2.9/benchmark_utils.html
+++ b/2.9/benchmark_utils.html
@@ -4396,7 +4396,7 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Nov 02, 2020 | Last Updated On: Jun 12, 2025</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Timer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">Timer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stmt='pass'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">setup='pass'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_setup=''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timer=&lt;built-in</span> <span class="pre">function</span> <span class="pre">perf_counter&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">globals=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sub_label=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">description=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">env=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_threads=1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">language=Language.PYTHON</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/timer.py#L67"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">Timer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stmt='pass'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">setup='pass'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_setup=''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timer=&lt;built-in</span> <span class="pre">function</span> <span class="pre">perf_counter&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">globals=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sub_label=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">description=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">env=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_threads=1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">language=Language.PYTHON</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/timer.py#L67"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer" title="Permalink to this definition">#</a></dt>
 <dd><p>Helper class for measuring execution time of PyTorch statements.</p>
 <p>For a full tutorial on how to use this class, see:
 <a class="reference external" href="https://pytorch.org/tutorials/recipes/recipes/benchmark.html">https://pytorch.org/tutorials/recipes/recipes/benchmark.html</a></p>
@@ -4500,7 +4500,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Timer.adaptive_autorange">
-<span class="sig-name descname"><span class="pre">adaptive_autorange</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_run_time</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_run_time</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/timer.py#L383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer.adaptive_autorange" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">adaptive_autorange</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_run_time</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_run_time</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/timer.py#L383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer.adaptive_autorange" title="Permalink to this definition">#</a></dt>
 <dd><p>Similar to <cite>blocked_autorange</cite> but also checks for variablility in measurements
 and repeats until iqr/median is smaller than <cite>threshold</cite> or <cite>max_run_time</cite> is reached.</p>
 <p>At a high level, adaptive_autorange executes the following pseudo-code:</p>
@@ -4541,7 +4541,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Timer.blocked_autorange">
-<span class="sig-name descname"><span class="pre">blocked_autorange</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_run_time</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/timer.py#L323"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer.blocked_autorange" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">blocked_autorange</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_run_time</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/timer.py#L323"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer.blocked_autorange" title="Permalink to this definition">#</a></dt>
 <dd><p>Measure many replicates while keeping timer overhead to a minimum.</p>
 <p>At a high level, blocked_autorange executes the following pseudo-code:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span>`setup`
@@ -4586,7 +4586,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Timer.collect_callgrind">
-<span class="sig-name descname"><span class="pre">collect_callgrind</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">number</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeats</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><span class="pre">None</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">collect_baseline</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_out_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="#torch.utils.benchmark.CallgrindStats" title="torch.utils.benchmark.utils.valgrind_wrapper.timer_interface.CallgrindStats"><span class="pre">CallgrindStats</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/timer.py#L468"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer.collect_callgrind" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">collect_callgrind</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">number</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeats</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><span class="pre">None</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">collect_baseline</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_out_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="#torch.utils.benchmark.CallgrindStats" title="torch.utils.benchmark.utils.valgrind_wrapper.timer_interface.CallgrindStats"><span class="pre">CallgrindStats</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/timer.py#L468"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer.collect_callgrind" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-name descname"><span class="pre">collect_callgrind</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">number</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeats</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">collect_baseline</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_out_file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.utils.benchmark.CallgrindStats" title="torch.utils.benchmark.utils.valgrind_wrapper.timer_interface.CallgrindStats"><span class="pre">torch.utils.benchmark.utils.valgrind_wrapper.timer_interface.CallgrindStats</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span></span></span></dt>
 <dd><p>Collect instruction counts using Callgrind.</p>
@@ -4621,7 +4621,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Timer.timeit">
-<span class="sig-name descname"><span class="pre">timeit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">number</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000000</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/timer.py#L258"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer.timeit" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">timeit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">number</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000000</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/timer.py#L258"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Timer.timeit" title="Permalink to this definition">#</a></dt>
 <dd><p>Mirrors the semantics of timeit.Timer.timeit().</p>
 <p>Execute the main statement (<cite>stmt</cite>) <cite>number</cite> times.
 <a class="reference external" href="https://docs.python.org/3/library/timeit.html#timeit.Timer.timeit">https://docs.python.org/3/library/timeit.html#timeit.Timer.timeit</a></p>
@@ -4636,7 +4636,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Measurement">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">Measurement</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">number_per_run</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raw_times</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">task_spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/common.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Measurement" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">Measurement</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">number_per_run</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raw_times</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">task_spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/common.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Measurement" title="Permalink to this definition">#</a></dt>
 <dd><p>The result of a Timer measurement.</p>
 <p>This class stores one or more measurements of a given statement. It is
 serializable and provides several convenience methods
@@ -4645,7 +4645,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Measurement.merge">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">merge</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">measurements</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/common.py#L230"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Measurement.merge" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">merge</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">measurements</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/common.py#L230"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Measurement.merge" title="Permalink to this definition">#</a></dt>
 <dd><p>Convenience method for merging replicates.</p>
 <p>Merge will extrapolate times to <cite>number_per_run=1</cite> and will not
 transfer any metadata. (Since it might differ between replicates)</p>
@@ -4675,7 +4675,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.benchmark.CallgrindStats">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">CallgrindStats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task_spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">number_per_run</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">built_with_debug_symbols</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">baseline_inclusive_stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">baseline_exclusive_stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stmt_inclusive_stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stmt_exclusive_stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stmt_callgrind_out</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">CallgrindStats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task_spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">number_per_run</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">built_with_debug_symbols</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">baseline_inclusive_stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">baseline_exclusive_stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stmt_inclusive_stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stmt_exclusive_stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stmt_callgrind_out</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats" title="Permalink to this definition">#</a></dt>
 <dd><p>Top level container for Callgrind results collected by Timer.</p>
 <p>Manipulation is generally done using the FunctionCounts class, which is
 obtained by calling <cite>CallgrindStats.stats(…)</cite>. Several convenience
@@ -4685,7 +4685,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.CallgrindStats.as_standardized">
-<span class="sig-name descname"><span class="pre">as_standardized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats.as_standardized" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">as_standardized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats.as_standardized" title="Permalink to this definition">#</a></dt>
 <dd><p>Strip library names and some prefixes from function strings.</p>
 <p>When comparing two different sets of instruction counts, on stumbling
 block can be path prefixes. Callgrind includes the full filepath
@@ -4714,7 +4714,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.CallgrindStats.counts">
-<span class="sig-name descname"><span class="pre">counts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">denoise</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats.counts" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">counts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">denoise</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats.counts" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the total number of instructions executed.</p>
 <p>See <cite>FunctionCounts.denoise()</cite> for an explanation of the <cite>denoise</cite> arg.</p>
 <dl class="field-list simple">
@@ -4726,7 +4726,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.CallgrindStats.delta">
-<span class="sig-name descname"><span class="pre">delta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">other</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inclusive</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats.delta" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">delta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">other</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inclusive</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats.delta" title="Permalink to this definition">#</a></dt>
 <dd><p>Diff two sets of counts.</p>
 <p>One common reason to collect instruction counts is to determine the
 the effect that a particular change will have on the number of instructions
@@ -4744,7 +4744,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.CallgrindStats.stats">
-<span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inclusive</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L198"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats.stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inclusive</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L198"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.CallgrindStats.stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns detailed function counts.</p>
 <p>Conceptually, the FunctionCounts returned can be thought of as a tuple
 of (count, path_and_function_name) tuples.</p>
@@ -4764,7 +4764,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.benchmark.FunctionCounts">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">FunctionCounts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">_data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inclusive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">truncate_rows</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_linewidth</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.FunctionCounts" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">FunctionCounts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">_data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inclusive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">truncate_rows</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_linewidth</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.FunctionCounts" title="Permalink to this definition">#</a></dt>
 <dd><p>Container for manipulating Callgrind results.</p>
 <dl class="simple">
 <dt>It supports:</dt><dd><ol class="arabic simple">
@@ -4781,7 +4781,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.FunctionCounts.denoise">
-<span class="sig-name descname"><span class="pre">denoise</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L132"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.FunctionCounts.denoise" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">denoise</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L132"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.FunctionCounts.denoise" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove known noisy instructions.</p>
 <p>Several instructions in the CPython interpreter are rather noisy. These
 instructions involve unicode to dictionary lookups which Python uses to
@@ -4797,7 +4797,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.FunctionCounts.filter">
-<span class="sig-name descname"><span class="pre">filter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filter_fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.FunctionCounts.filter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">filter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filter_fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.FunctionCounts.filter" title="Permalink to this definition">#</a></dt>
 <dd><p>Keep only the elements where <cite>filter_fn</cite> applied to function name returns True.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4808,7 +4808,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.FunctionCounts.transform">
-<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">map_fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.FunctionCounts.transform" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">map_fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.FunctionCounts.transform" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply <cite>map_fn</cite> to all of the function names.</p>
 <p>This can be used to regularize function names (e.g. stripping irrelevant
 parts of the file path), coalesce entries by mapping multiple functions
@@ -4824,7 +4824,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Compare">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">Compare</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">results</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/compare.py#L269"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.benchmark.</span></span><span class="sig-name descname"><span class="pre">Compare</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">results</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/compare.py#L269"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare" title="Permalink to this definition">#</a></dt>
 <dd><p>Helper class for displaying the results of many measurements in a
 formatted table.</p>
 <p>The table format is based on the information fields provided in
@@ -4840,33 +4840,33 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Compare.colorize">
-<span class="sig-name descname"><span class="pre">colorize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rowwise</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/compare.py#L311"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.colorize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">colorize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rowwise</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/compare.py#L311"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.colorize" title="Permalink to this definition">#</a></dt>
 <dd><p>Colorize formatted table.</p>
 <p>Colorize columnwise by default.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Compare.extend_results">
-<span class="sig-name descname"><span class="pre">extend_results</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">results</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/compare.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.extend_results" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extend_results</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">results</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/compare.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.extend_results" title="Permalink to this definition">#</a></dt>
 <dd><p>Append results to already stored ones.</p>
 <p>All added results must be instances of <code class="docutils literal notranslate"><span class="pre">Measurement</span></code>.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Compare.highlight_warnings">
-<span class="sig-name descname"><span class="pre">highlight_warnings</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/compare.py#L318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.highlight_warnings" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">highlight_warnings</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/compare.py#L318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.highlight_warnings" title="Permalink to this definition">#</a></dt>
 <dd><p>Enables warning highlighting when building formatted table.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Compare.print">
-<span class="sig-name descname"><span class="pre">print</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/compare.py#L322"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.print" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">print</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/compare.py#L322"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.print" title="Permalink to this definition">#</a></dt>
 <dd><p>Print formatted table</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.benchmark.Compare.trim_significant_figures">
-<span class="sig-name descname"><span class="pre">trim_significant_figures</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/benchmark/utils/compare.py#L307"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.trim_significant_figures" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">trim_significant_figures</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/benchmark/utils/compare.py#L307"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.benchmark.Compare.trim_significant_figures" title="Permalink to this definition">#</a></dt>
 <dd><p>Enables trimming of significant figures when building the formatted table.</p>
 </dd></dl>
 
diff --git a/2.9/checkpoint.html b/2.9/checkpoint.html
index fb5536ae459..8fe2d746f6c 100644
--- a/2.9/checkpoint.html
+++ b/2.9/checkpoint.html
@@ -4426,7 +4426,7 @@ <h1>torch.utils.checkpoint<a class="headerlink" href="#torch-utils-checkpoint" t
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.checkpoint.checkpoint">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">checkpoint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">function</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_reentrant=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">context_fn=&lt;function</span> <span class="pre">noop_context_fn&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">determinism_check='default'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">early_stop=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">**kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/checkpoint.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.checkpoint" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">checkpoint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">function</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_reentrant=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">context_fn=&lt;function</span> <span class="pre">noop_context_fn&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">determinism_check='default'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">early_stop=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">**kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/checkpoint.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.checkpoint" title="Permalink to this definition">#</a></dt>
 <dd><p>Checkpoint a model or part of the model.</p>
 <p>Activation checkpointing is a technique that trades compute for memory.
 Instead of keeping tensors needed for backward alive until they are used in
@@ -4547,7 +4547,7 @@ <h1>torch.utils.checkpoint<a class="headerlink" href="#torch-utils-checkpoint" t
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.checkpoint.checkpoint_sequential">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">checkpoint_sequential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">functions</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">segments</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_reentrant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/checkpoint.py#L511"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.checkpoint_sequential" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">checkpoint_sequential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">functions</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">segments</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_reentrant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/checkpoint.py#L511"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.checkpoint_sequential" title="Permalink to this definition">#</a></dt>
 <dd><p>Checkpoint a sequential model to save memory.</p>
 <p>Sequential models execute a list of modules/functions in order
 (sequentially). Therefore, we can divide such a model in various segments
@@ -4597,7 +4597,7 @@ <h1>torch.utils.checkpoint<a class="headerlink" href="#torch-utils-checkpoint" t
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.checkpoint.set_checkpoint_debug_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">set_checkpoint_debug_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/checkpoint.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.set_checkpoint_debug_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">set_checkpoint_debug_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/checkpoint.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.set_checkpoint_debug_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager that sets whether checkpoint should print additional debug
 information when running. See the <code class="docutils literal notranslate"><span class="pre">debug</span></code> flag for
 <a class="reference internal" href="#torch.utils.checkpoint.checkpoint" title="torch.utils.checkpoint.checkpoint"><code class="xref py py-func docutils literal notranslate"><span class="pre">checkpoint()</span></code></a> for more information. Note that
@@ -4613,7 +4613,7 @@ <h1>torch.utils.checkpoint<a class="headerlink" href="#torch-utils-checkpoint" t
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.checkpoint.CheckpointPolicy">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">CheckpointPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/checkpoint.py#L1251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.CheckpointPolicy" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">CheckpointPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/checkpoint.py#L1251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.CheckpointPolicy" title="Permalink to this definition">#</a></dt>
 <dd><p>Enum for specifying the policy for checkpointing during backpropagation.</p>
 <p>The following policies are supported:</p>
 <ul class="simple">
@@ -4637,7 +4637,7 @@ <h1>torch.utils.checkpoint<a class="headerlink" href="#torch-utils-checkpoint" t
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.checkpoint.SelectiveCheckpointContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">SelectiveCheckpointContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_recompute</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/checkpoint.py#L1225"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.SelectiveCheckpointContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">SelectiveCheckpointContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_recompute</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/checkpoint.py#L1225"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.SelectiveCheckpointContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Context passed to policy function during selective checkpointing.</p>
 <p>This class is used to pass relevant metadata to the policy function during
 selective checkpointing. The metadata includes whether the current invocation
@@ -4660,7 +4660,7 @@ <h1>torch.utils.checkpoint<a class="headerlink" href="#torch-utils-checkpoint" t
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.checkpoint.create_selective_checkpoint_contexts">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">create_selective_checkpoint_contexts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">policy_fn_or_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_cache_entry_mutation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/checkpoint.py#L1365"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.create_selective_checkpoint_contexts" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.checkpoint.</span></span><span class="sig-name descname"><span class="pre">create_selective_checkpoint_contexts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">policy_fn_or_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_cache_entry_mutation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/checkpoint.py#L1365"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.checkpoint.create_selective_checkpoint_contexts" title="Permalink to this definition">#</a></dt>
 <dd><p>Helper to avoid recomputing certain ops during activation checkpointing.</p>
 <p>Use this with <cite>torch.utils.checkpoint.checkpoint</cite> to control which
 operations are recomputed during the backward pass.</p>
diff --git a/2.9/cond.html b/2.9/cond.html
index bc6ea654c39..32f0d5759ea 100644
--- a/2.9/cond.html
+++ b/2.9/cond.html
@@ -4564,7 +4564,7 @@ <h2>Invariants of torch.ops.higher_order.cond<a class="headerlink" href="#invari
 <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._higher_order_ops.cond.cond">
-<span class="sig-prename descclassname"><span class="pre">torch._higher_order_ops.cond.</span></span><span class="sig-name descname"><span class="pre">cond</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pred</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">true_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">false_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">operands</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_higher_order_ops/cond.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._higher_order_ops.cond.cond" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._higher_order_ops.cond.</span></span><span class="sig-name descname"><span class="pre">cond</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pred</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">true_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">false_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">operands</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_higher_order_ops/cond.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._higher_order_ops.cond.cond" title="Permalink to this definition">#</a></dt>
 <dd><p>Conditionally applies <cite>true_fn</cite> or <cite>false_fn</cite>.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/config_mod.html b/2.9/config_mod.html
index 57eae9ff84e..cd6cbd0e499 100644
--- a/2.9/config_mod.html
+++ b/2.9/config_mod.html
@@ -4396,7 +4396,7 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Apr 09, 2019 | Last Updated On: Jun 13, 2025</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.__config__.show">
-<span class="sig-prename descclassname"><span class="pre">torch.__config__.</span></span><span class="sig-name descname"><span class="pre">show</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__config__.py#L4"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__config__.show" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.__config__.</span></span><span class="sig-name descname"><span class="pre">show</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__config__.py#L4"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__config__.show" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a human-readable string with descriptions of the
 configuration of PyTorch.</p>
 <dl class="field-list simple">
@@ -4408,7 +4408,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.__config__.parallel_info">
-<span class="sig-prename descclassname"><span class="pre">torch.__config__.</span></span><span class="sig-name descname"><span class="pre">parallel_info</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__config__.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__config__.parallel_info" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.__config__.</span></span><span class="sig-name descname"><span class="pre">parallel_info</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__config__.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__config__.parallel_info" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns detailed string with parallelization settings</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/cpp_extension.html b/2.9/cpp_extension.html
index 044271d1e08..38b719bb8e1 100644
--- a/2.9/cpp_extension.html
+++ b/2.9/cpp_extension.html
@@ -4396,7 +4396,7 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Mar 07, 2018 | Last Updated On: Feb 16, 2025</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.CppExtension">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">CppExtension</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L1157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.CppExtension" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">CppExtension</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L1157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.CppExtension" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="xref py py-class docutils literal notranslate"><span class="pre">setuptools.Extension</span></code> for C++.</p>
 <p>Convenience method that creates a <code class="xref py py-class docutils literal notranslate"><span class="pre">setuptools.Extension</span></code> with the
 bare minimum (but often sufficient) arguments to build a C++ extension.</p>
@@ -4441,7 +4441,7 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.CUDAExtension">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">CUDAExtension</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L1227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.CUDAExtension" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">CUDAExtension</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L1227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.CUDAExtension" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="xref py py-class docutils literal notranslate"><span class="pre">setuptools.Extension</span></code> for CUDA/C++.</p>
 <p>Convenience method that creates a <code class="xref py py-class docutils literal notranslate"><span class="pre">setuptools.Extension</span></code> with the
 bare minimum (but often sufficient) arguments to build a CUDA/C++
@@ -4546,7 +4546,7 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.SyclExtension">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">SyclExtension</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L1419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.SyclExtension" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">SyclExtension</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L1419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.SyclExtension" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a <code class="xref py py-class docutils literal notranslate"><span class="pre">setuptools.Extension</span></code> for SYCL/C++.</p>
 <p>Convenience method that creates a <code class="xref py py-class docutils literal notranslate"><span class="pre">setuptools.Extension</span></code> with the
 bare minimum (but often sufficient) arguments to build a SYCL/C++
@@ -4598,7 +4598,7 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.BuildExtension">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">BuildExtension</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.BuildExtension" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">BuildExtension</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.BuildExtension" title="Permalink to this definition">#</a></dt>
 <dd><p>A custom <code class="xref py py-mod docutils literal notranslate"><span class="pre">setuptools</span></code> build extension .</p>
 <p>This <code class="xref py py-class docutils literal notranslate"><span class="pre">setuptools.build_ext</span></code> subclass takes care of passing the
 minimum required compiler flags (e.g. <code class="docutils literal notranslate"><span class="pre">-std=c++17</span></code>) as well as mixed
@@ -4626,7 +4626,7 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.load">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_cuda_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_sycl_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_ldflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_include_paths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">build_directory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_cuda</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_sycl</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_python_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_standalone</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_intermediates</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L1583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.load" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_cuda_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_sycl_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_ldflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_include_paths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">build_directory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_cuda</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_sycl</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_python_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_standalone</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_intermediates</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L1583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.load" title="Permalink to this definition">#</a></dt>
 <dd><p>Load a PyTorch C++ extension just-in-time (JIT).</p>
 <p>To load an extension, a Ninja build file is emitted, which is used to
 compile the given sources into a dynamic library. This library is
@@ -4726,7 +4726,7 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.load_inline">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">load_inline</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cpp_sources</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cuda_sources</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sycl_sources</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">functions</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_cuda_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_sycl_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_ldflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_include_paths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">build_directory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_cuda</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_sycl</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_python_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_pytorch_error_handling</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_intermediates</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_pch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_implicit_headers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L1866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.load_inline" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">load_inline</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cpp_sources</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cuda_sources</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sycl_sources</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">functions</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_cuda_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_sycl_cflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_ldflags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_include_paths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">build_directory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_cuda</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_sycl</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_python_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_pytorch_error_handling</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_intermediates</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_pch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_implicit_headers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L1866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.load_inline" title="Permalink to this definition">#</a></dt>
 <dd><p>Load a PyTorch C++ extension just-in-time (JIT) from string sources.</p>
 <p>This function behaves exactly like <a class="reference internal" href="#torch.utils.cpp_extension.load" title="torch.utils.cpp_extension.load"><code class="xref py py-func docutils literal notranslate"><span class="pre">load()</span></code></a>, but takes its sources as
 strings rather than filenames. These strings are stored to files in the
@@ -4823,7 +4823,7 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.include_paths">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">include_paths</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cpu'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L1499"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.include_paths" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">include_paths</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cpu'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L1499"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.include_paths" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the include paths required to build a C++ or CUDA or SYCL extension.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4840,7 +4840,7 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.get_compiler_abi_compatibility_and_version">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">get_compiler_abi_compatibility_and_version</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">compiler</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L444"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.get_compiler_abi_compatibility_and_version" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">get_compiler_abi_compatibility_and_version</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">compiler</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L444"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.get_compiler_abi_compatibility_and_version" title="Permalink to this definition">#</a></dt>
 <dd><p>Determine if the given compiler is ABI-compatible with PyTorch alongside its version.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4859,13 +4859,13 @@ <h1>torch.utils.cpp_extension<a class="headerlink" href="#torch-utils-cpp-extens
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.verify_ninja_availability">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">verify_ninja_availability</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L2302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.verify_ninja_availability" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">verify_ninja_availability</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L2302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.verify_ninja_availability" title="Permalink to this definition">#</a></dt>
 <dd><p>Raise <code class="docutils literal notranslate"><span class="pre">RuntimeError</span></code> if <a class="reference external" href="https://ninja-build.org/">ninja</a> build system is not available on the system, does nothing otherwise.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.cpp_extension.is_ninja_available">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">is_ninja_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_extension.py#L2292"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.is_ninja_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.cpp_extension.</span></span><span class="sig-name descname"><span class="pre">is_ninja_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_extension.py#L2292"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.cpp_extension.is_ninja_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return <code class="docutils literal notranslate"><span class="pre">True</span></code> if the <a class="reference external" href="https://ninja-build.org/">ninja</a> build system is available on the system, <code class="docutils literal notranslate"><span class="pre">False</span></code> otherwise.</p>
 </dd></dl>
 
diff --git a/2.9/cuda._sanitizer.html b/2.9/cuda._sanitizer.html
index f2228bbbb4b..a5e19903027 100644
--- a/2.9/cuda._sanitizer.html
+++ b/2.9/cuda._sanitizer.html
@@ -4505,7 +4505,7 @@ <h2>Usage<a class="headerlink" href="#usage" title="Permalink to this heading">#
 <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda._sanitizer.enable_cuda_sanitizer">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda._sanitizer.</span></span><span class="sig-name descname"><span class="pre">enable_cuda_sanitizer</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/_sanitizer.py#L651"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda._sanitizer.enable_cuda_sanitizer" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda._sanitizer.</span></span><span class="sig-name descname"><span class="pre">enable_cuda_sanitizer</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/_sanitizer.py#L651"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda._sanitizer.enable_cuda_sanitizer" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable CUDA Sanitizer.</p>
 <p>The sanitizer will begin to analyze low-level CUDA calls invoked by torch functions
 for synchronization errors. All data races found will be printed to the standard
diff --git a/2.9/cuda.html b/2.9/cuda.html
index c2f4e111b33..fabd59f6df2 100644
--- a/2.9/cuda.html
+++ b/2.9/cuda.html
@@ -4744,7 +4744,7 @@ <h2>Memory management<a class="headerlink" href="#memory-management" title="Perm
 </div>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.use_mem_pool">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">use_mem_pool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pool</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L1211"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.use_mem_pool" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">use_mem_pool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pool</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L1211"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.use_mem_pool" title="Permalink to this definition">#</a></dt>
 <dd><p>A context manager that routes allocations to a given pool.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/cuda.tunable.html b/2.9/cuda.tunable.html
index 1827dd066d2..74534480b08 100644
--- a/2.9/cuda.tunable.html
+++ b/2.9/cuda.tunable.html
@@ -4570,7 +4570,7 @@ <h4>Environment Variable Interface<a class="headerlink" href="#environment-varia
 <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.enable">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">enable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L219"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.enable" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">enable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L219"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.enable" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the big on/off switch for all TunableOp implementations.</p>
 <dl class="field-list simple">
 </dl>
@@ -4578,7 +4578,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.is_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">is_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.is_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">is_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.is_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether the TunableOp feature is enabled.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4589,7 +4589,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.tuning_enable">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">tuning_enable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L229"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.tuning_enable" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">tuning_enable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L229"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.tuning_enable" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable tuning of TunableOp implementations.</p>
 <p>When enabled, if a tuned entry isn’t found, run the tuning step and record
 the entry.</p>
@@ -4599,7 +4599,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.tuning_is_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">tuning_is_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.tuning_is_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">tuning_is_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.tuning_is_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether TunableOp implementations can be tuned.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4610,7 +4610,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.record_untuned_enable">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">record_untuned_enable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L243"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.record_untuned_enable" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">record_untuned_enable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L243"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.record_untuned_enable" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable recording untuned of TunableOp perations for offline tuning.</p>
 <p>When enabled, if a tuned entry isn’t found, write it to the untuned file.</p>
 <dl class="field-list simple">
@@ -4619,7 +4619,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.record_untuned_is_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">record_untuned_is_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.record_untuned_is_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">record_untuned_is_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.record_untuned_is_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether TunableOp operations are recorded for offline tuning.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4630,7 +4630,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.set_max_tuning_duration">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">set_max_tuning_duration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">duration</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L256"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.set_max_tuning_duration" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">set_max_tuning_duration</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">duration</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L256"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.set_max_tuning_duration" title="Permalink to this definition">#</a></dt>
 <dd><p>Set max time in milliseconds to spend tuning a given solution.</p>
 <p>If both max tuning duration and iterations are set, the smaller of the two
 will be honored. At minimum 1 tuning iteration will always be run.</p>
@@ -4640,7 +4640,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.get_max_tuning_duration">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_max_tuning_duration</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_max_tuning_duration" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_max_tuning_duration</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_max_tuning_duration" title="Permalink to this definition">#</a></dt>
 <dd><p>Get max time to spend tuning a given solution.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4651,7 +4651,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.set_max_tuning_iterations">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">set_max_tuning_iterations</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">iterations</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.set_max_tuning_iterations" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">set_max_tuning_iterations</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">iterations</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.set_max_tuning_iterations" title="Permalink to this definition">#</a></dt>
 <dd><p>Set max number of iterations to spend tuning a given solution.</p>
 <p>If both max tuning duration and iterations are set, the smaller of the two
 will be honored. At minimum 1 tuning iteration will always be run.</p>
@@ -4661,7 +4661,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.get_max_tuning_iterations">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_max_tuning_iterations</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L279"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_max_tuning_iterations" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_max_tuning_iterations</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L279"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_max_tuning_iterations" title="Permalink to this definition">#</a></dt>
 <dd><p>Get max iterations to spend tuning a given solution.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4672,7 +4672,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.set_filename">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">set_filename</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">insert_device_ordinal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L284"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.set_filename" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">set_filename</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">insert_device_ordinal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L284"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.set_filename" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the filename to use for input/output of tuning results.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">insert_device_ordinal</span></code> is <code class="docutils literal notranslate"><span class="pre">True</span></code> then the current device ordinal
 will be added to the given filename automatically. This can be used in a
@@ -4683,7 +4683,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.get_filename">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_filename</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_filename" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_filename</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_filename" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the results filename.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4694,7 +4694,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.get_results">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_results</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L299"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_results" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_results</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L299"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_results" title="Permalink to this definition">#</a></dt>
 <dd><p>Return all TunableOp results.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4705,7 +4705,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.get_validators">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_validators</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_validators" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_validators</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_validators" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the TunableOp validators.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4716,7 +4716,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.write_file_on_exit">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">write_file_on_exit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.write_file_on_exit" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">write_file_on_exit</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.write_file_on_exit" title="Permalink to this definition">#</a></dt>
 <dd><p>During Tuning Context destruction, write file to disk.</p>
 <p>This is useful as a final flush of your results to disk if your application
 terminates as result of normal operation or an error. Manual flushing of
@@ -4727,7 +4727,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.write_file">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">write_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.write_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">write_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.write_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Write results to a CSV file.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">filename</span></code> is not given, <code class="docutils literal notranslate"><span class="pre">get_filename()</span></code> is called.</p>
 <dl class="field-list simple">
@@ -4739,7 +4739,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.read_file">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">read_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L328"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.read_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">read_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L328"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.read_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Read results from a TunableOp CSV file.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">filename</span></code> is not given, <code class="docutils literal notranslate"><span class="pre">get_filename()</span></code> is called.</p>
 <dl class="field-list simple">
@@ -4751,7 +4751,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.tune_gemm_in_file">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">tune_gemm_in_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L351"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.tune_gemm_in_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">tune_gemm_in_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L351"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.tune_gemm_in_file" title="Permalink to this definition">#</a></dt>
 <dd><p>tune GEMM in file.</p>
 <dl class="field-list simple">
 </dl>
@@ -4759,7 +4759,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.mgpu_tune_gemm_in_file">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">mgpu_tune_gemm_in_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename_pattern</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_gpus</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L780"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.mgpu_tune_gemm_in_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">mgpu_tune_gemm_in_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename_pattern</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_gpus</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L780"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.mgpu_tune_gemm_in_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Process one or more files and distribute work over one or more GPUs.</p>
 <dl class="field-list simple">
 </dl>
@@ -4767,7 +4767,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.set_rotating_buffer_size">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">set_rotating_buffer_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">buffer_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.set_rotating_buffer_size" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">set_rotating_buffer_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">buffer_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.set_rotating_buffer_size" title="Permalink to this definition">#</a></dt>
 <dd><p>Set rotating buffer size to this value in MB, if the buffer size is greater than zero.</p>
 <p>If less than zero, query L2 cache size. If equal to zero, means deactivate rotating buffer.</p>
 <dl class="field-list simple">
@@ -4776,7 +4776,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.tunable.get_rotating_buffer_size">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_rotating_buffer_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/tunable.py#L346"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_rotating_buffer_size" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.tunable.</span></span><span class="sig-name descname"><span class="pre">get_rotating_buffer_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/tunable.py#L346"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.tunable.get_rotating_buffer_size" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the rotating buffer size in kilobytes.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/data.html b/2.9/data.html
index 3e118bb3e52..1aa79155692 100644
--- a/2.9/data.html
+++ b/2.9/data.html
@@ -4762,7 +4762,7 @@
 </div>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.DataLoader">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">DataLoader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sampler</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_sampler</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_workers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">collate_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pin_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_last</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">worker_init_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">multiprocessing_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefetch_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent_workers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pin_memory_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_order</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataloader.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.DataLoader" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">DataLoader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sampler</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_sampler</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_workers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">collate_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pin_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_last</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">worker_init_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">multiprocessing_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefetch_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent_workers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pin_memory_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_order</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataloader.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.DataLoader" title="Permalink to this definition">#</a></dt>
 <dd><p>Data loader combines a dataset and a sampler, and provides an iterable over the given dataset.</p>
 <p>The <a class="reference internal" href="#torch.utils.data.DataLoader" title="torch.utils.data.DataLoader"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataLoader</span></code></a> supports both map-style and
 iterable-style datasets with single- or multi-process loading, customizing
@@ -4864,7 +4864,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.Dataset">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">Dataset</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataset.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.Dataset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">Dataset</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataset.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.Dataset" title="Permalink to this definition">#</a></dt>
 <dd><p>An abstract class representing a <a class="reference internal" href="#torch.utils.data.Dataset" title="torch.utils.data.Dataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dataset</span></code></a>.</p>
 <p>All datasets that represent a map from keys to data samples should subclass
 it. All subclasses should overwrite <code class="xref py py-meth docutils literal notranslate"><span class="pre">__getitem__()</span></code>, supporting fetching a
@@ -4885,7 +4885,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.IterableDataset">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">IterableDataset</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataset.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.IterableDataset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">IterableDataset</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataset.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.IterableDataset" title="Permalink to this definition">#</a></dt>
 <dd><p>An iterable Dataset.</p>
 <p>All datasets that represent an iterable of data samples should subclass it.
 Such form of datasets is particularly useful when data come from a stream.</p>
@@ -4987,7 +4987,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.TensorDataset">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">TensorDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataset.py#L189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.TensorDataset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">TensorDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataset.py#L189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.TensorDataset" title="Permalink to this definition">#</a></dt>
 <dd><p>Dataset wrapping tensors.</p>
 <p>Each sample will be retrieved by indexing tensors along the first dimension.</p>
 <dl class="field-list simple">
@@ -4999,7 +4999,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.StackDataset">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">StackDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataset.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.StackDataset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">StackDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataset.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.StackDataset" title="Permalink to this definition">#</a></dt>
 <dd><p>Dataset as a stacking of multiple datasets.</p>
 <p>This class is useful to assemble different parts of complex input data, given as datasets.</p>
 <p class="rubric">Example</p>
@@ -5023,7 +5023,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.ConcatDataset">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">ConcatDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">datasets</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataset.py#L300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.ConcatDataset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">ConcatDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">datasets</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataset.py#L300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.ConcatDataset" title="Permalink to this definition">#</a></dt>
 <dd><p>Dataset as a concatenation of multiple datasets.</p>
 <p>This class is useful to assemble different existing datasets.</p>
 <dl class="field-list simple">
@@ -5035,7 +5035,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.ChainDataset">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">ChainDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">datasets</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataset.py#L357"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.ChainDataset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">ChainDataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">datasets</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataset.py#L357"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.ChainDataset" title="Permalink to this definition">#</a></dt>
 <dd><p>Dataset for chaining multiple <a class="reference internal" href="#torch.utils.data.IterableDataset" title="torch.utils.data.IterableDataset"><code class="xref py py-class docutils literal notranslate"><span class="pre">IterableDataset</span></code></a> s.</p>
 <p>This class is useful to assemble different existing dataset streams. The
 chaining operation is done on-the-fly, so concatenating large-scale
@@ -5049,7 +5049,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.Subset">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">Subset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataset.py#L389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.Subset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">Subset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataset.py#L389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.Subset" title="Permalink to this definition">#</a></dt>
 <dd><p>Subset of a dataset at specified indices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5063,7 +5063,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.data._utils.collate.collate">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.data._utils.collate.</span></span><span class="sig-name descname"><span class="pre">collate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">collate_fn_map</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/_utils/collate.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data._utils.collate.collate" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.data._utils.collate.</span></span><span class="sig-name descname"><span class="pre">collate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">collate_fn_map</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/_utils/collate.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data._utils.collate.collate" title="Permalink to this definition">#</a></dt>
 <dd><p>General collate function that handles collection type of element within each batch.</p>
 <p>The function also opens function registry to deal with specific element types. <cite>default_collate_fn_map</cite>
 provides default collate functions for tensors, numpy arrays, numbers and strings.</p>
@@ -5098,7 +5098,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.data.default_collate">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">default_collate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/_utils/collate.py#L337"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.default_collate" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">default_collate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/_utils/collate.py#L337"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.default_collate" title="Permalink to this definition">#</a></dt>
 <dd><p>Take in a batch of data and put the elements within the batch into a tensor with an additional outer dimension - batch size.</p>
 <p>The exact output type can be a <a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a>, a <cite>Sequence</cite> of <a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a>, a
 Collection of <a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a>, or left unchanged, depending on the input type.
@@ -5164,7 +5164,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.data.default_convert">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">default_convert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/_utils/collate.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.default_convert" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">default_convert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/_utils/collate.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.default_convert" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert each NumPy array element into a <a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a>.</p>
 <p>If the input is a <cite>Sequence</cite>, <cite>Collection</cite>, or <cite>Mapping</cite>, it tries to convert each element inside to a <a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a>.
 If the input is not an NumPy array, it is left unchanged.
@@ -5199,7 +5199,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.data.get_worker_info">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">get_worker_info</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/_utils/worker.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.get_worker_info" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">get_worker_info</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/_utils/worker.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.get_worker_info" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the information about the current
 <a class="reference internal" href="#torch.utils.data.DataLoader" title="torch.utils.data.DataLoader"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataLoader</span></code></a> iterator worker process.</p>
 <p>When called in a worker, this returns an object guaranteed to have the
@@ -5233,7 +5233,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.data.random_split">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">random_split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator=&lt;torch._C.Generator</span> <span class="pre">object&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/dataset.py#L422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.random_split" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">random_split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator=&lt;torch._C.Generator</span> <span class="pre">object&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/dataset.py#L422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.random_split" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly split a dataset into non-overlapping new datasets of given lengths.</p>
 <p>If a list of fractions that sum up to 1 is given,
 the lengths will be computed automatically as
@@ -5265,7 +5265,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.Sampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">Sampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/sampler.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.Sampler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">Sampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/sampler.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.Sampler" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class for all Samplers.</p>
 <p>Every Sampler subclass has to provide an <code class="xref py py-meth docutils literal notranslate"><span class="pre">__iter__()</span></code> method, providing a
 way to iterate over indices or lists of indices (batches) of dataset elements,
@@ -5312,7 +5312,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.SequentialSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">SequentialSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_source</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/sampler.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.SequentialSampler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">SequentialSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_source</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/sampler.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.SequentialSampler" title="Permalink to this definition">#</a></dt>
 <dd><p>Samples elements sequentially, always in the same order.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5323,7 +5323,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.RandomSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">RandomSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">replacement</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/sampler.py#L129"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.RandomSampler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">RandomSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">replacement</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/sampler.py#L129"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.RandomSampler" title="Permalink to this definition">#</a></dt>
 <dd><p>Samples elements randomly. If without replacement, then sample from a shuffled dataset.</p>
 <p>If with replacement, then user can specify <code class="xref py py-attr docutils literal notranslate"><span class="pre">num_samples</span></code> to draw.</p>
 <dl class="field-list simple">
@@ -5340,7 +5340,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.SubsetRandomSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">SubsetRandomSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/sampler.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.SubsetRandomSampler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">SubsetRandomSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/sampler.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.SubsetRandomSampler" title="Permalink to this definition">#</a></dt>
 <dd><p>Samples elements randomly from a given list of indices, without replacement.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5354,7 +5354,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.WeightedRandomSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">WeightedRandomSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weights</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_samples</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">replacement</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/sampler.py#L226"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.WeightedRandomSampler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">WeightedRandomSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weights</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_samples</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">replacement</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/sampler.py#L226"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.WeightedRandomSampler" title="Permalink to this definition">#</a></dt>
 <dd><p>Samples elements from <code class="docutils literal notranslate"><span class="pre">[0,..,len(weights)-1]</span></code> with given probabilities (weights).</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5387,7 +5387,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.BatchSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">BatchSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sampler</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_last</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/sampler.py#L299"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.BatchSampler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.</span></span><span class="sig-name descname"><span class="pre">BatchSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sampler</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_last</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/sampler.py#L299"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.BatchSampler" title="Permalink to this definition">#</a></dt>
 <dd><p>Wraps another sampler to yield a mini-batch of indices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5416,7 +5416,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.data.distributed.DistributedSampler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.distributed.</span></span><span class="sig-name descname"><span class="pre">DistributedSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_replicas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_last</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/data/distributed.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.distributed.DistributedSampler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.data.distributed.</span></span><span class="sig-name descname"><span class="pre">DistributedSampler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dataset</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_replicas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_last</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/data/distributed.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.data.distributed.DistributedSampler" title="Permalink to this definition">#</a></dt>
 <dd><p>Sampler that restricts data loading to a subset of the dataset.</p>
 <p>It is especially useful in conjunction with
 <a class="reference internal" href="generated/torch.nn.parallel.DistributedDataParallel.html#torch.nn.parallel.DistributedDataParallel" title="torch.nn.parallel.DistributedDataParallel"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.parallel.DistributedDataParallel</span></code></a>. In such a case, each
diff --git a/2.9/ddp_comm_hooks.html b/2.9/ddp_comm_hooks.html
index fe89b45b874..b2c5645d833 100644
--- a/2.9/ddp_comm_hooks.html
+++ b/2.9/ddp_comm_hooks.html
@@ -4496,7 +4496,7 @@ <h2>Default Communication Hooks<a class="headerlink" href="#default-communicatio
 The input <code class="docutils literal notranslate"><span class="pre">bucket</span></code> is a <a class="reference internal" href="#torch.distributed.GradBucket" title="torch.distributed.GradBucket"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.distributed.GradBucket</span></code></a> object.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.default_hooks.allreduce_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">allreduce_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">process_group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.allreduce_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">allreduce_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">process_group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.allreduce_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Call <code class="docutils literal notranslate"><span class="pre">allreduce</span></code> using <code class="docutils literal notranslate"><span class="pre">GradBucket</span></code> tensors.</p>
 <p>Once gradient tensors are aggregated across all workers, its <code class="docutils literal notranslate"><span class="pre">then</span></code>
 callback takes the mean and returns the result.</p>
@@ -4520,7 +4520,7 @@ <h2>Default Communication Hooks<a class="headerlink" href="#default-communicatio
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.default_hooks.fp16_compress_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">fp16_compress_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">process_group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.fp16_compress_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">fp16_compress_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">process_group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.fp16_compress_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Compress by casting <code class="docutils literal notranslate"><span class="pre">GradBucket</span></code> to <code class="docutils literal notranslate"><span class="pre">torch.float16</span></code> divided by process group size.</p>
 <p>This DDP communication hook implements a simple gradient compression
 approach that casts <code class="docutils literal notranslate"><span class="pre">GradBucket</span></code> tensor to half-precision floating-point format (<code class="docutils literal notranslate"><span class="pre">torch.float16</span></code>)
@@ -4542,7 +4542,7 @@ <h2>Default Communication Hooks<a class="headerlink" href="#default-communicatio
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.default_hooks.bf16_compress_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">bf16_compress_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">process_group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.bf16_compress_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">bf16_compress_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">process_group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.bf16_compress_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Warning: This API is experimental, and it requires NCCL version later than 2.9.6.</p>
 <p>This DDP communication hook implements a simple gradient compression
 approach that casts <code class="docutils literal notranslate"><span class="pre">GradBucket</span></code> tensor to half-precision
@@ -4567,7 +4567,7 @@ <h2>Default Communication Hooks<a class="headerlink" href="#default-communicatio
 which can be combined with other communication hooks.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.default_hooks.fp16_compress_wrapper">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">fp16_compress_wrapper</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.fp16_compress_wrapper" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">fp16_compress_wrapper</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.fp16_compress_wrapper" title="Permalink to this definition">#</a></dt>
 <dd><p>Cast input tensor to <code class="docutils literal notranslate"><span class="pre">torch.float16</span></code>, cast result of hook back to input dtype.</p>
 <p>This wrapper casts the input gradient tensor of a given DDP communication hook to half-precision
 floating point format (<code class="docutils literal notranslate"><span class="pre">torch.float16</span></code>), and casts the resulting tensor of the given hook back to
@@ -4589,7 +4589,7 @@ <h2>Default Communication Hooks<a class="headerlink" href="#default-communicatio
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.default_hooks.bf16_compress_wrapper">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">bf16_compress_wrapper</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.bf16_compress_wrapper" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.default_hooks.</span></span><span class="sig-name descname"><span class="pre">bf16_compress_wrapper</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.py#L169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.default_hooks.bf16_compress_wrapper" title="Permalink to this definition">#</a></dt>
 <dd><p>Warning: This API is experimental, and it requires NCCL version later than 2.9.6.</p>
 <p>This wrapper casts the input gradient tensor of a given DDP communication hook to half-precision
 <a class="reference external" href="https://en.wikipedia.org/wiki/Bfloat16_floating-point_format">Brain floating point format</a>  (<code class="docutils literal notranslate"><span class="pre">torch.bfloat16</span></code>),
@@ -4622,7 +4622,7 @@ <h2>PowerSGD Communication Hook<a class="headerlink" href="#powersgd-communicati
 <h3>PowerSGD State<a class="headerlink" href="#powersgd-state" title="Permalink to this heading">#</a></h3>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.</span></span><span class="sig-name descname"><span class="pre">PowerSGDState</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">process_group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">matrix_approximation_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_powerSGD_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_compression_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_error_feedback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">warm_start</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">orthogonalization_epsilon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compression_stats_logging_frequency</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_tensors_with_same_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.</span></span><span class="sig-name descname"><span class="pre">PowerSGDState</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">process_group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">matrix_approximation_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_powerSGD_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_compression_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_error_feedback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">warm_start</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">orthogonalization_epsilon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">random_seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compression_stats_logging_frequency</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_tensors_with_same_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState" title="Permalink to this definition">#</a></dt>
 <dd><p>Store both the algorithm’s hyperparameters and internal state for all gradients during training.</p>
 <p>Particularly, <code class="docutils literal notranslate"><span class="pre">matrix_approximation_rank</span></code> and <code class="docutils literal notranslate"><span class="pre">start_powerSGD_iter</span></code> are the main hyperparameters that should be tuned by the user.
 For performance, we suggest to keep binary hyperparameters <code class="docutils literal notranslate"><span class="pre">use_error_feedback</span></code> and <code class="docutils literal notranslate"><span class="pre">warm_start</span></code> on.</p>
@@ -4674,7 +4674,7 @@ <h3>PowerSGD Hooks<a class="headerlink" href="#powersgd-hooks" title="Permalink
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.powerSGD_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.</span></span><span class="sig-name descname"><span class="pre">powerSGD_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L339"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.powerSGD_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.</span></span><span class="sig-name descname"><span class="pre">powerSGD_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L339"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.powerSGD_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Implement PowerSGD algorithm.</p>
 <p>This DDP communication hook implements PowerSGD gradient compression
 algorithm described in the <a class="reference external" href="https://arxiv.org/abs/1905.13727">paper</a>.
@@ -4739,7 +4739,7 @@ <h3>PowerSGD Hooks<a class="headerlink" href="#powersgd-hooks" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.batched_powerSGD_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.</span></span><span class="sig-name descname"><span class="pre">batched_powerSGD_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L653"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.batched_powerSGD_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.</span></span><span class="sig-name descname"><span class="pre">batched_powerSGD_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L653"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.batched_powerSGD_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Implement simplified PowerSGD algorithm.</p>
 <p>This DDP communication hook implements a simplified PowerSGD gradient compression
 algorithm described in the <a class="reference external" href="https://arxiv.org/abs/1905.13727">paper</a>.
@@ -4807,7 +4807,7 @@ <h2>Debugging Communication Hooks<a class="headerlink" href="#debugging-communic
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.debugging_hooks.noop_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.debugging_hooks.</span></span><span class="sig-name descname"><span class="pre">noop_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">_</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/debugging_hooks.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.debugging_hooks.noop_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.debugging_hooks.</span></span><span class="sig-name descname"><span class="pre">noop_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">_</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/debugging_hooks.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.debugging_hooks.noop_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a future that wraps the input, so it is a no-op that does not incur any communication overheads.</p>
 <p>This hook should <strong>only</strong> be used for headroom analysis of allreduce optimization,
 instead of the normal gradient synchronization.
@@ -4845,12 +4845,12 @@ <h2>Checkpointing of Communication Hooks<a class="headerlink" href="#checkpointi
 <p><a class="reference internal" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState" title="torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState"><code class="xref py py-class docutils literal notranslate"><span class="pre">PowerSGDState</span></code></a> has <code class="docutils literal notranslate"><span class="pre">__setstate__</span></code> and <code class="docutils literal notranslate"><span class="pre">__getstate__</span></code> implemented and can be used as a reference.</p>
 <dl class="py class">
 <dt class="sig sig-object py">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.</span></span><span class="sig-name descname"><span class="pre">PowerSGDState</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.</span></span><span class="sig-name descname"><span class="pre">PowerSGDState</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState.__getstate__">
-<span class="sig-name descname"><span class="pre">__getstate__</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState.__getstate__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__getstate__</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState.__getstate__" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a <code class="docutils literal notranslate"><span class="pre">Dict[str,</span> <span class="pre">Any]</span></code> which will be pickled and saved.</p>
 <p><code class="docutils literal notranslate"><span class="pre">process_group</span></code> is not serializable and excluded from
 a returned state.</p>
@@ -4858,7 +4858,7 @@ <h2>Checkpointing of Communication Hooks<a class="headerlink" href="#checkpointi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState.__setstate__">
-<span class="sig-name descname"><span class="pre">__setstate__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L291"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState.__setstate__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__setstate__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.py#L291"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.ddp_comm_hooks.powerSGD_hook.PowerSGDState.__setstate__" title="Permalink to this definition">#</a></dt>
 <dd><p>Take a provided <code class="docutils literal notranslate"><span class="pre">state</span></code> and set to this <code class="docutils literal notranslate"><span class="pre">PowerSGDState</span></code> instance.</p>
 <p><code class="docutils literal notranslate"><span class="pre">process_group</span></code> is set to default.</p>
 </dd></dl>
diff --git a/2.9/distributed._dist2.html b/2.9/distributed._dist2.html
index b186db024c6..019d87dc917 100644
--- a/2.9/distributed._dist2.html
+++ b/2.9/distributed._dist2.html
@@ -4865,14 +4865,14 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed._dist2.ProcessGroupFactory">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">ProcessGroupFactory</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/_dist2.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.ProcessGroupFactory" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">ProcessGroupFactory</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/_dist2.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.ProcessGroupFactory" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Protocol" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Protocol</span></code></a></p>
 <p>Protocol for process group factories.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed._dist2.current_process_group">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">current_process_group</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/_dist2.py#L158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.current_process_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">current_process_group</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/_dist2.py#L158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.current_process_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the current process group. Thread local method.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4886,7 +4886,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed._dist2.new_group">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">new_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/_dist2.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.new_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">new_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/_dist2.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.new_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a new process group with the given backend and options. This group is
 independent and will not be globally registered and thus not usable via the
 standard torch.distributed.* APIs.</p>
@@ -4911,7 +4911,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed._dist2.process_group">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">process_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/_dist2.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.process_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">process_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/_dist2.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.process_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager for process groups. Thread local method.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4925,7 +4925,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed._dist2.register_backend">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">register_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/_dist2.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.register_backend" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed._dist2.</span></span><span class="sig-name descname"><span class="pre">register_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/_dist2.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed._dist2.register_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a new process group backend.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/distributed.algorithms.join.html b/2.9/distributed.algorithms.join.html
index 80c7d887f4c..dabce633a70 100644
--- a/2.9/distributed.algorithms.join.html
+++ b/2.9/distributed.algorithms.join.html
@@ -4400,7 +4400,7 @@ <h1>Generic Join Context Manager<a class="headerlink" href="#generic-join-contex
 <a class="reference external" href="https://pytorch.org/tutorials/advanced/generic_join.html">Distributed Training with Uneven Inputs Using the Join Context Manager</a>.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.Join">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.</span></span><span class="sig-name descname"><span class="pre">Join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">joinables</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">throw_on_early_termination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/join.py#L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.Join" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.</span></span><span class="sig-name descname"><span class="pre">Join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">joinables</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">throw_on_early_termination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/join.py#L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.Join" title="Permalink to this definition">#</a></dt>
 <dd><p>This class defines the generic join context manager, which allows custom hooks to be called after a process joins.</p>
 <p>These hooks should shadow the
 collective communications of non-joined processes to prevent hanging and
@@ -4463,7 +4463,7 @@ <h1>Generic Join Context Manager<a class="headerlink" href="#generic-join-contex
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.Join.notify_join_context">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">notify_join_context</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">joinable</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/join.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.Join.notify_join_context" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">notify_join_context</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">joinable</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/join.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.Join.notify_join_context" title="Permalink to this definition">#</a></dt>
 <dd><p>Notifies the join context manager that the calling process has not yet joined.</p>
 <p>Then, if <code class="docutils literal notranslate"><span class="pre">throw_on_early_termination=True</span></code>, checks if uneven inputs have been detected
 (i.e. if one process has already joined) and throws an exception if so.</p>
@@ -4491,7 +4491,7 @@ <h1>Generic Join Context Manager<a class="headerlink" href="#generic-join-contex
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.Joinable">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.</span></span><span class="sig-name descname"><span class="pre">Joinable</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/join.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.Joinable" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.</span></span><span class="sig-name descname"><span class="pre">Joinable</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/join.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.Joinable" title="Permalink to this definition">#</a></dt>
 <dd><p>This defines an abstract base class for joinable classes.</p>
 <p>A joinable class
 (inheriting from <a class="reference internal" href="#torch.distributed.algorithms.Joinable" title="torch.distributed.algorithms.Joinable"><code class="xref py py-class docutils literal notranslate"><span class="pre">Joinable</span></code></a>) should implement <a class="reference internal" href="#torch.distributed.algorithms.Joinable.join_hook" title="torch.distributed.algorithms.Joinable.join_hook"><code class="xref py py-meth docutils literal notranslate"><span class="pre">join_hook()</span></code></a>,
@@ -4508,7 +4508,7 @@ <h1>Generic Join Context Manager<a class="headerlink" href="#generic-join-contex
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.Joinable.join_hook">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">join_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/join.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.Joinable.join_hook" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">join_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/join.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.Joinable.join_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a <a class="reference internal" href="#torch.distributed.algorithms.JoinHook" title="torch.distributed.algorithms.JoinHook"><code class="xref py py-class docutils literal notranslate"><span class="pre">JoinHook</span></code></a> instance for the given <a class="reference internal" href="#torch.distributed.algorithms.Joinable" title="torch.distributed.algorithms.Joinable"><code class="xref py py-class docutils literal notranslate"><span class="pre">Joinable</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4533,7 +4533,7 @@ <h1>Generic Join Context Manager<a class="headerlink" href="#generic-join-contex
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.JoinHook">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.</span></span><span class="sig-name descname"><span class="pre">JoinHook</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/join.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.JoinHook" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.algorithms.</span></span><span class="sig-name descname"><span class="pre">JoinHook</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/join.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.JoinHook" title="Permalink to this definition">#</a></dt>
 <dd><p>This defines a join hook, which provides two entry points in the join context manager.</p>
 <p>Entry points : a main hook, which is called repeatedly while there exists a non-joined
 process, and a post-hook, which is called once all processes have joined.</p>
@@ -4542,7 +4542,7 @@ <h1>Generic Join Context Manager<a class="headerlink" href="#generic-join-contex
 <code class="docutils literal notranslate"><span class="pre">post_hook()</span></code> as appropriate.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.JoinHook.main_hook">
-<span class="sig-name descname"><span class="pre">main_hook</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/join.py#L26"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.JoinHook.main_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">main_hook</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/join.py#L26"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.JoinHook.main_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Call this hook while there exists a non-joined process to shadow collective communications in a training iteration.</p>
 <p>Training iteration i.e., in one forward pass, backward pass, and optimizer step.</p>
 <dl class="field-list simple">
@@ -4551,7 +4551,7 @@ <h1>Generic Join Context Manager<a class="headerlink" href="#generic-join-contex
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.algorithms.JoinHook.post_hook">
-<span class="sig-name descname"><span class="pre">post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">is_last_joiner</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/algorithms/join.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.JoinHook.post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">is_last_joiner</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/algorithms/join.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.algorithms.JoinHook.post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Call hook after all processes have joined.</p>
 <p>It is passed an additional <code class="docutils literal notranslate"><span class="pre">bool</span></code> argument <code class="docutils literal notranslate"><span class="pre">is_last_joiner</span></code>, which indicates if the rank is one of the last to join.</p>
 <dl class="field-list simple">
diff --git a/2.9/distributed.checkpoint.html b/2.9/distributed.checkpoint.html
index f32e1d61299..d7e831d11c3 100644
--- a/2.9/distributed.checkpoint.html
+++ b/2.9/distributed.checkpoint.html
@@ -4412,13 +4412,13 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </ul>
 <span class="target" id="module-torch.distributed.checkpoint"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict_saver.AsyncCheckpointerType">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">AsyncCheckpointerType</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict_saver.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.AsyncCheckpointerType" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">AsyncCheckpointerType</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict_saver.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.AsyncCheckpointerType" title="Permalink to this definition">#</a></dt>
 <dd><p>Enum for async checkpointer type.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict_saver.AsyncSaveResponse">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">AsyncSaveResponse</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">staging_completion</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">upload_completion</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict_saver.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.AsyncSaveResponse" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">AsyncSaveResponse</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">staging_completion</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">upload_completion</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict_saver.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.AsyncSaveResponse" title="Permalink to this definition">#</a></dt>
 <dd><p>This class contains futures for staging and upload completion.
 It is returned by async_save().
 staging_completion is a future that indicates when local copy
@@ -4431,7 +4431,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict_saver.save">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_writer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_collectives</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict_saver.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.save" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_writer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_collectives</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict_saver.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.save" title="Permalink to this definition">#</a></dt>
 <dd><p>Save a distributed model in SPMD style.</p>
 <p>This function is different from <code class="docutils literal notranslate"><span class="pre">torch.save()</span></code> as it handles
 <code class="docutils literal notranslate"><span class="pre">ShardedTensor</span></code> , and <code class="docutils literal notranslate"><span class="pre">DTensor</span></code> by having each rank only save their local shards.</p>
@@ -4522,7 +4522,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict_saver.async_save">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">async_save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_writer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_checkpointer_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">AsyncCheckpointerType.THREAD</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_stager</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_collectives</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict_saver.py#L217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.async_save" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">async_save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_writer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_checkpointer_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">AsyncCheckpointerType.THREAD</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_stager</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_collectives</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict_saver.py#L217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.async_save" title="Permalink to this definition">#</a></dt>
 <dd><p>Asynchronous version of <code class="docutils literal notranslate"><span class="pre">save</span></code>. This code first de-stages the state_dict on to the
 staging storage (defaults to CPU memory), and then calls the <cite>save</cite> in a separate thread.</p>
 <div class="admonition warning">
@@ -4589,7 +4589,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict_saver.save_state_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">save_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_writer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">coordinator_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict_saver.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.save_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_saver.</span></span><span class="sig-name descname"><span class="pre">save_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_writer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">coordinator_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict_saver.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_saver.save_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>This method is deprecated. Please switch to ‘save’.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4600,7 +4600,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict_loader.load">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_loader.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_reader</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict_loader.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_loader.load" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_loader.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_reader</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict_loader.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_loader.load" title="Permalink to this definition">#</a></dt>
 <dd><p>Load a checkpoint into a distributed state dict in SPMD style.</p>
 <p>Each rank must have the same keys in their <code class="docutils literal notranslate"><span class="pre">state_dict</span></code> provided to this
 API. Mismatched keys may result in hangs or errors. If unsure, you can use
@@ -4689,7 +4689,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict_loader.load_state_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_loader.</span></span><span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_reader</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">coordinator_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict_loader.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_loader.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict_loader.</span></span><span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_reader</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">coordinator_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_dist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict_loader.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict_loader.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>This method is deprecated. Please switch to ‘load’.</p>
 <dl class="field-list simple">
 </dl>
@@ -4698,7 +4698,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 <p>The following module is also useful for additional customization of the staging mechanisms used for asynchronous checkpointing (<code class="docutils literal notranslate"><span class="pre">torch.distributed.checkpoint.async_save</span></code>):</p>
 <span class="target" id="module-torch.distributed.checkpoint.staging"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.AsyncStager">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.staging.</span></span><span class="sig-name descname"><span class="pre">AsyncStager</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.AsyncStager" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.staging.</span></span><span class="sig-name descname"><span class="pre">AsyncStager</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.AsyncStager" title="Permalink to this definition">#</a></dt>
 <dd><p>This protocol is meant to provide customization and extensibility for dcp.async_save, allowing users
 to customize how data is staged previous to executing the usual dcp.save path in parallel.
 The expected order of operations (concretely defined in <cite>torch.distributed.state_dict_saver.async_save</cite>)
@@ -4731,7 +4731,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </ol>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.AsyncStager.close">
-<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.AsyncStager.close" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.AsyncStager.close" title="Permalink to this definition">#</a></dt>
 <dd><p>Clean up all resources used by the stager.</p>
 <dl class="field-list simple">
 </dl>
@@ -4745,7 +4745,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.AsyncStager.stage">
-<span class="sig-name descname"><span class="pre">stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.AsyncStager.stage" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.AsyncStager.stage" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a “staged” copy of <cite>state_dict</cite>. The expectation of the staged copy is that it is
 inoculated from any updates incurred after the stage call is complete.</p>
 <dl class="field-list simple">
@@ -4757,7 +4757,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.AsyncStager.synchronize_staging">
-<span class="sig-name descname"><span class="pre">synchronize_staging</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.AsyncStager.synchronize_staging" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize_staging</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.AsyncStager.synchronize_staging" title="Permalink to this definition">#</a></dt>
 <dd><p>In the case <cite>stage</cite> is async in some way, this method should be called to ensure staging
 is complete and it is safe to begin modifying the original <cite>state_dict</cite></p>
 <dl class="field-list simple">
@@ -4768,7 +4768,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.DefaultStager">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.staging.</span></span><span class="sig-name descname"><span class="pre">DefaultStager</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">StagingOptions(use_pinned_memory=True,</span> <span class="pre">use_shared_memory=True,</span> <span class="pre">use_async_staging=True,</span> <span class="pre">use_non_blocking_copy=True)</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L133"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.DefaultStager" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.staging.</span></span><span class="sig-name descname"><span class="pre">DefaultStager</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">StagingOptions(use_pinned_memory=True,</span> <span class="pre">use_shared_memory=True,</span> <span class="pre">use_async_staging=True,</span> <span class="pre">use_non_blocking_copy=True)</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L133"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.DefaultStager" title="Permalink to this definition">#</a></dt>
 <dd><p>DefaultStager provides a full-featured staging implementation that combines
 multiple optimization techniques for efficient checkpoint preparation.</p>
 <p>The staging process works as follows:
@@ -4808,7 +4808,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.DefaultStager.close">
-<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.DefaultStager.close" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.DefaultStager.close" title="Permalink to this definition">#</a></dt>
 <dd><p>Clean up all resources used by the DefaultStager. Shuts down the ThreadPoolExecutor
 used for async staging operations and cleans up the underlying StateDictStager’s
 cached storages. Should be called when the stager is no longer needed to prevent
@@ -4827,7 +4827,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.DefaultStager.stage">
-<span class="sig-name descname"><span class="pre">stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L200"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.DefaultStager.stage" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L200"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.DefaultStager.stage" title="Permalink to this definition">#</a></dt>
 <dd><p>This function is responsible for staging staging the state_dict.
 See class docstring for more details on staging.
 If use_async_staging is True, it will return a Future object that will be
@@ -4845,7 +4845,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.DefaultStager.synchronize_staging">
-<span class="sig-name descname"><span class="pre">synchronize_staging</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L262"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.DefaultStager.synchronize_staging" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize_staging</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L262"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.DefaultStager.synchronize_staging" title="Permalink to this definition">#</a></dt>
 <dd><p>When use_async_staging is True, this method will wait until staging is complete.
 If use_async_staging is False, this method is a no-op.</p>
 <dl class="field-list simple">
@@ -4856,7 +4856,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.StagingOptions">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.staging.</span></span><span class="sig-name descname"><span class="pre">StagingOptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">use_pinned_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_shared_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_async_staging</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_non_blocking_copy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.StagingOptions" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.staging.</span></span><span class="sig-name descname"><span class="pre">StagingOptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">use_pinned_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_shared_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_async_staging</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_non_blocking_copy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.StagingOptions" title="Permalink to this definition">#</a></dt>
 <dd><p>Configuration options for checkpoint staging behavior.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Variables</dt>
@@ -4883,7 +4883,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.BlockingAsyncStager">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.staging.</span></span><span class="sig-name descname"><span class="pre">BlockingAsyncStager</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_staged_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.BlockingAsyncStager" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.staging.</span></span><span class="sig-name descname"><span class="pre">BlockingAsyncStager</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_staged_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.BlockingAsyncStager" title="Permalink to this definition">#</a></dt>
 <dd><p>An implementation of AsyncStager which stages the state_dict on CPU RAM and blocks until the copy is complete.
 This implementation also provides an option to optimize stage latency using pinned memory.</p>
 <p>N.B. synchronize_staging is a no-op in this case.</p>
@@ -4891,7 +4891,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.BlockingAsyncStager.stage">
-<span class="sig-name descname"><span class="pre">stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.BlockingAsyncStager.stage" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.BlockingAsyncStager.stage" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a copy of <cite>state_dict</cite> on the CPU.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4902,7 +4902,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.staging.BlockingAsyncStager.synchronize_staging">
-<span class="sig-name descname"><span class="pre">synchronize_staging</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/staging.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.BlockingAsyncStager.synchronize_staging" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize_staging</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/staging.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.staging.BlockingAsyncStager.synchronize_staging" title="Permalink to this definition">#</a></dt>
 <dd><p>No-op function, since staging is blocking.</p>
 <dl class="field-list simple">
 </dl>
@@ -4913,11 +4913,11 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 <p>In addition to the above entrypoints, <code class="docutils literal notranslate"><span class="pre">Stateful</span></code> objects, as described below, provide additional customization during saving/loading</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.stateful.Stateful">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.stateful.</span></span><span class="sig-name descname"><span class="pre">Stateful</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/stateful.py#L8"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.stateful.Stateful" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.stateful.</span></span><span class="sig-name descname"><span class="pre">Stateful</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/stateful.py#L8"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.stateful.Stateful" title="Permalink to this definition">#</a></dt>
 <dd><p>Stateful protocol for objects that can be checkpointed and restored.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.stateful.Stateful.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/stateful.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.stateful.Stateful.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/stateful.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.stateful.Stateful.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Restore the object’s state from the provided state_dict.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4928,7 +4928,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.stateful.Stateful.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/stateful.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.stateful.Stateful.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/stateful.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.stateful.Stateful.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Objects should return their state_dict representation as a dictionary.
 The output of this function will be checkpointed, and later restored in
 <cite>load_state_dict()</cite>.</p>
@@ -4953,7 +4953,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 <p>The following types define the IO interface used during checkpoint:</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageReader">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">StorageReader</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">StorageReader</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader" title="Permalink to this definition">#</a></dt>
 <dd><p>Interface used by <code class="docutils literal notranslate"><span class="pre">load_state_dict</span></code> to read from storage.</p>
 <p>One StorageReader instance acts as both the coordinator and the follower
 in a distributed checkpoint. As part of initialization, each instance
@@ -4969,7 +4969,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </ol>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageReader.prepare_global_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">prepare_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plans</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.prepare_global_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">prepare_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plans</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.prepare_global_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform centralized planning of storage loading.</p>
 <p>This method is only called on the coordinator instance.</p>
 <p>While this method can produce a completely different plan, the preferred
@@ -4989,7 +4989,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageReader.prepare_local_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">prepare_local_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.prepare_local_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">prepare_local_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.prepare_local_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform storage-specific local planning.</p>
 <p>While this method can produce a completely different plan, the recommended
 way is to store storage specific data in LoadPlan::storage_data.</p>
@@ -5008,7 +5008,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageReader.read_data">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">read_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.read_data" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">read_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.read_data" title="Permalink to this definition">#</a></dt>
 <dd><p>Read all items from <code class="docutils literal notranslate"><span class="pre">plan</span></code> using <code class="docutils literal notranslate"><span class="pre">planner</span></code> to resolve the data.</p>
 <p>A subclass should call <code class="docutils literal notranslate"><span class="pre">LoadPlanner::load_bytes</span></code> to deserialize a BytesIO
 object into the right place.</p>
@@ -5034,7 +5034,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageReader.read_metadata">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">read_metadata</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.read_metadata" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">read_metadata</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.read_metadata" title="Permalink to this definition">#</a></dt>
 <dd><p>Read the checkpoint metadata.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5048,7 +5048,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageReader.reset">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L186"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.reset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L186"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.reset" title="Permalink to this definition">#</a></dt>
 <dd><p>Calls to indicates a brand new checkpoint read is going to happen.
 A checkpoint_id may be present if users set the checkpoint_id for
 this checkpoint read. The meaning of the checkpiont_id is
@@ -5066,7 +5066,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageReader.set_up_storage_reader">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_up_storage_reader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.set_up_storage_reader" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_up_storage_reader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.set_up_storage_reader" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize this instance.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5081,7 +5081,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageReader.validate_checkpoint_id">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">validate_checkpoint_id</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.validate_checkpoint_id" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">validate_checkpoint_id</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageReader.validate_checkpoint_id" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the given checkpoint_id is supported by the storage. This allow
 us to enable automatic storage selection.</p>
 <dl class="field-list simple">
@@ -5095,7 +5095,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">StorageWriter</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">StorageWriter</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter" title="Permalink to this definition">#</a></dt>
 <dd><p>Interface used by <code class="docutils literal notranslate"><span class="pre">save_state_dict</span></code> to write to storage.</p>
 <p>One StorageWriter instance acts as both the coordinator and the follower
 in a distributed checkpoint. As part of initialization, each instance
@@ -5111,7 +5111,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </ol>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter.finish">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">finish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">results</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.finish" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">finish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">results</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.finish" title="Permalink to this definition">#</a></dt>
 <dd><p>Write the metadata and marks the current checkpoint as successful.</p>
 <p>The actual format/schema used for serializing <cite>metadata</cite> is an
 implementation detail. The only requirement is that it’s recoverable
@@ -5134,7 +5134,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter.prepare_global_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">prepare_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plans</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.prepare_global_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">prepare_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plans</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.prepare_global_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform centralized planning of storage.</p>
 <p>This method is only called on the coordinator instance.</p>
 <p>While this method can produce a completely different plan, the preferred
@@ -5154,7 +5154,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter.prepare_local_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">prepare_local_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.prepare_local_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">prepare_local_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.prepare_local_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform storage-specific local planning.</p>
 <p>While this method can produce a completely different plan, the recommended
 way is to store storage specific data in SavePlan::storage_data.</p>
@@ -5173,7 +5173,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter.reset">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.reset" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.reset" title="Permalink to this definition">#</a></dt>
 <dd><p>Calls to indicates a brand new checkpoint write is going to happen.
 A checkpoint_id may be present if users set the checkpoint_id for
 this checkpoint write. The meaning of the checkpiont_id is
@@ -5191,7 +5191,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter.set_up_storage_writer">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_up_storage_writer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.set_up_storage_writer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_up_storage_writer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.set_up_storage_writer" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize this instance.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5203,7 +5203,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter.storage_meta">
-<span class="sig-name descname"><span class="pre">storage_meta</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.storage_meta" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">storage_meta</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.storage_meta" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the storage-specific metadata. This is used to store additional information
 in a checkpoint that can be useful for providing request-level observability. StorageMeta
 is passed to the <code class="docutils literal notranslate"><span class="pre">SavePlanner</span></code> during save calls. Returns None by default.</p>
@@ -5217,7 +5217,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter.validate_checkpoint_id">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">validate_checkpoint_id</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.validate_checkpoint_id" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">validate_checkpoint_id</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.validate_checkpoint_id" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the given checkpoint_id is supported by the storage. This allow
 us to enable automatic storage selection.</p>
 <dl class="field-list simple">
@@ -5229,7 +5229,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.StorageWriter.write_data">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">write_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/storage.py#L107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.write_data" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">write_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/storage.py#L107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.StorageWriter.write_data" title="Permalink to this definition">#</a></dt>
 <dd><p>Write all items from <code class="docutils literal notranslate"><span class="pre">plan</span></code> using <code class="docutils literal notranslate"><span class="pre">planner</span></code> to resolve the data.</p>
 <p>A subclass should call <code class="docutils literal notranslate"><span class="pre">SavePlanner::resolve_data</span></code> on each item
 from the plan to get access to the underlying object to write.</p>
@@ -5260,7 +5260,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 <p>The following types define the planner interface used during checkpoint:</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">LoadPlanner</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">LoadPlanner</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner" title="Permalink to this definition">#</a></dt>
 <dd><p>Abstract class defining the protocol used by load_state_dict to plan the load process.</p>
 <p>LoadPlanner are stateful objects that can be used to customize the whole load process.</p>
 <p>LoadPlanner acts as an access proxy to the state_dict, so any transformation done to it
@@ -5337,7 +5337,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner.commit_tensor">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">commit_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L440"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.commit_tensor" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">commit_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L440"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.commit_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Call once the StorageReader finished loading data into <code class="docutils literal notranslate"><span class="pre">tensor</span></code>.</p>
 <p>The provided tensor is the same one returned by the call to <code class="docutils literal notranslate"><span class="pre">resolve_tensor</span></code>.
 This method is only needed if this LoadPlanner needs to post process <code class="docutils literal notranslate"><span class="pre">tensor</span></code> prior to
@@ -5349,7 +5349,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner.create_global_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">global_plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L399"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.create_global_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">global_plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L399"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.create_global_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the global load plan and return plans for each rank.</p>
 <p>. N.B. This is called on the coordinator rank only</p>
 <dl class="field-list simple">
@@ -5361,7 +5361,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner.create_local_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create_local_plan</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L391"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.create_local_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create_local_plan</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L391"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.create_local_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a LoadPlan based on state_dict and metadata provided by set_up_planner.</p>
 <p>. N.B. This is called on every rank.</p>
 <dl class="field-list simple">
@@ -5373,7 +5373,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner.finish_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">finish_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">central_plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L407"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.finish_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">finish_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">central_plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L407"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.finish_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Accept the plan from coordinator and return final LoadPlan.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5384,7 +5384,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner.load_bytes">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L411"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.load_bytes" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">load_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L411"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.load_bytes" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the item described by <code class="docutils literal notranslate"><span class="pre">read_item``and</span> <span class="pre">``value</span></code>.</p>
 <p>This method is expected to modify in-place the underlying state_dict.</p>
 <p>The contents of <code class="docutils literal notranslate"><span class="pre">value</span></code> are defined by the SavePlanner used to produce
@@ -5395,7 +5395,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner.resolve_bytes">
-<span class="sig-name descname"><span class="pre">resolve_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.resolve_bytes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">resolve_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.resolve_bytes" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the BytesIO to be used by the StorageReader to load <cite>read_item</cite>.</p>
 <p>The BytesIO should alias with one on the underlying state_dict as StorageReader will replace its contents.</p>
 <dl class="field-list simple">
@@ -5407,7 +5407,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner.resolve_tensor">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">resolve_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L430"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.resolve_tensor" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">resolve_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L430"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.resolve_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the tensor described by <code class="docutils literal notranslate"><span class="pre">read_item</span></code> to be used by the StorageReader to load <cite>read_item</cite>.</p>
 <p>The tensor should alias with one on the underlying state_dict as StorageReader will replace its contents.
 If, for any reason, that’s not possible, the planner can use the <code class="docutils literal notranslate"><span class="pre">commit_tensor</span></code> method to copy the data
@@ -5421,7 +5421,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlanner.set_up_planner">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_up_planner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L378"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.set_up_planner" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_up_planner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L378"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlanner.set_up_planner" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize this instance to load data into <code class="docutils literal notranslate"><span class="pre">state_dict</span></code>.</p>
 <p>. N.B. This is called on every rank.</p>
 <dl class="field-list simple">
@@ -5432,21 +5432,21 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.LoadPlan">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">LoadPlan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">items</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.distributed.checkpoint.ReadItem" title="torch.distributed.checkpoint.planner.ReadItem"><span class="pre">torch.distributed.checkpoint.planner.ReadItem</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L114"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">LoadPlan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">items</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.distributed.checkpoint.ReadItem" title="torch.distributed.checkpoint.planner.ReadItem"><span class="pre">torch.distributed.checkpoint.planner.ReadItem</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L114"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.LoadPlan" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.ReadItem">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">ReadItem</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">type</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.distributed.checkpoint.planner.LoadItemType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dest_index</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.distributed.checkpoint.metadata.MetadataIndex</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dest_offsets</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="size.html#torch.Size" title="torch.Size"><span class="pre">torch.Size</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_index</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.distributed.checkpoint.metadata.MetadataIndex</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_offsets</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="size.html#torch.Size" title="torch.Size"><span class="pre">torch.Size</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="size.html#torch.Size" title="torch.Size"><span class="pre">torch.Size</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.ReadItem" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">ReadItem</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">type</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.distributed.checkpoint.planner.LoadItemType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dest_index</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.distributed.checkpoint.metadata.MetadataIndex</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dest_offsets</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="size.html#torch.Size" title="torch.Size"><span class="pre">torch.Size</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_index</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.distributed.checkpoint.metadata.MetadataIndex</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_offsets</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="size.html#torch.Size" title="torch.Size"><span class="pre">torch.Size</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="size.html#torch.Size" title="torch.Size"><span class="pre">torch.Size</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.ReadItem" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.SavePlanner">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">SavePlanner</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">SavePlanner</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner" title="Permalink to this definition">#</a></dt>
 <dd><p>Abstract class defining the protocol used by save_state_dict to plan the save process.</p>
 <p>SavePlanners are stateful objects that can be used to customize the whole save process.</p>
 <p>SavePlanner acts as an access proxy to the state_dict, so any transformation done to it
@@ -5545,7 +5545,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.SavePlanner.create_global_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">all_plans</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.create_global_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">all_plans</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.create_global_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the global checkpoint plan and return the local plan of each rank.</p>
 <p>This is called on the coordinator rank only.</p>
 <dl class="field-list simple">
@@ -5557,7 +5557,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.SavePlanner.create_local_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create_local_plan</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L254"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.create_local_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create_local_plan</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L254"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.create_local_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the save plan for the current rank.</p>
 <p>This will be aggregated and passed to create_global_plan.
 Planner specific data can be passed through SavePlan::planner_data.</p>
@@ -5571,7 +5571,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.SavePlanner.finish_plan">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">finish_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.finish_plan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">finish_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.finish_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Merge the plan created by <cite>create_local_plan</cite> and the result of <cite>create_global_plan</cite>.</p>
 <p>This is called on all ranks.</p>
 <dl class="field-list simple">
@@ -5583,7 +5583,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.SavePlanner.resolve_data">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">resolve_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">write_item</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.resolve_data" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">resolve_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">write_item</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.resolve_data" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform and prepare <code class="docutils literal notranslate"><span class="pre">write_item</span></code> from <code class="docutils literal notranslate"><span class="pre">state_dict</span></code> for storage, ensuring idempotency and thread-safety.</p>
 <p>Lookup the object associated with <code class="docutils literal notranslate"><span class="pre">write_item</span></code> in <code class="docutils literal notranslate"><span class="pre">state_dict</span></code> and apply any
 transformation (such as serialization) prior to the storage layer consuming it.</p>
@@ -5603,7 +5603,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.SavePlanner.set_up_planner">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_up_planner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_meta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L239"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.set_up_planner" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_up_planner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_meta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L239"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlanner.set_up_planner" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize this planner to save <code class="docutils literal notranslate"><span class="pre">state_dict</span></code>.</p>
 <p>Implementations should save those values as they won’t be provided lated in the save process.</p>
 <p>This is called on all ranks.</p>
@@ -5615,20 +5615,20 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.SavePlan">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">SavePlan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">items</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.distributed.checkpoint.planner.WriteItem" title="torch.distributed.checkpoint.planner.WriteItem"><span class="pre">torch.distributed.checkpoint.planner.WriteItem</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">usable</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlan" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">SavePlan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">items</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.distributed.checkpoint.planner.WriteItem" title="torch.distributed.checkpoint.planner.WriteItem"><span class="pre">torch.distributed.checkpoint.planner.WriteItem</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">storage_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Any</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">usable</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.SavePlan" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.planner.WriteItem">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.planner.</span></span><span class="sig-name descname"><span class="pre">WriteItem</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bytes_io_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.planner.WriteItem" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.planner.</span></span><span class="sig-name descname"><span class="pre">WriteItem</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bytes_io_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.planner.WriteItem" title="Permalink to this definition">#</a></dt>
 <dd><p>Dataclass which holds information about what needs to be written to storage.</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.planner.WriteItem.tensor_storage_size">
-<span class="sig-name descname"><span class="pre">tensor_storage_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.planner.WriteItem.tensor_storage_size" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">tensor_storage_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.planner.WriteItem.tensor_storage_size" title="Permalink to this definition">#</a></dt>
 <dd><p>Calculates the storage size of the underlying tensor, or None if this is not a tensor write.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5644,7 +5644,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.planner.BytesIOWriteData">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.planner.</span></span><span class="sig-name descname"><span class="pre">BytesIOWriteData</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">nbytes</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/planner.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.planner.BytesIOWriteData" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.planner.</span></span><span class="sig-name descname"><span class="pre">BytesIOWriteData</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">nbytes</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/planner.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.planner.BytesIOWriteData" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
@@ -5652,7 +5652,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 <p>We provide a filesystem based storage layer:</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.FileSystemReader">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">FileSystemReader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_extension_registry</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/filesystem.py#L833"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.FileSystemReader" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">FileSystemReader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_extension_registry</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/filesystem.py#L833"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.FileSystemReader" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py property">
@@ -5665,7 +5665,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.FileSystemWriter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">FileSystemWriter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">single_file_per_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sync_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">thread_count</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">per_thread_copy_ahead</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10000000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_staged_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">overwrite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_extensions</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">serialization_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">SerializationFormat.TORCH_SAVE</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/filesystem.py#L959"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.FileSystemWriter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">FileSystemWriter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">single_file_per_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sync_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">thread_count</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">per_thread_copy_ahead</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10000000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_staged_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">overwrite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_extensions</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">serialization_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">SerializationFormat.TORCH_SAVE</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/filesystem.py#L959"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.FileSystemWriter" title="Permalink to this definition">#</a></dt>
 <dd><p>Basic implementation of StorageWriter using file IO.</p>
 <p>This implementation makes the following assumptions and simplifications:</p>
 <ul class="simple">
@@ -5679,7 +5679,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.FileSystemWriter.stage">
-<span class="sig-name descname"><span class="pre">stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/filesystem.py#L1019"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.FileSystemWriter.stage" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/filesystem.py#L1019"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.FileSystemWriter.stage" title="Permalink to this definition">#</a></dt>
 <dd><p>Override of AsyncStager.stage</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5701,12 +5701,12 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 can handle all of torch.distributed constructs such as FSDP, DDP, ShardedTensor and DistributedTensor.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.DefaultSavePlanner">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">DefaultSavePlanner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flatten_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flatten_sharded_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dedup_replicated_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dedup_save_to_lowest_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_plan_caching</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/default_planner.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultSavePlanner" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">DefaultSavePlanner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flatten_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flatten_sharded_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dedup_replicated_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dedup_save_to_lowest_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_plan_caching</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/default_planner.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultSavePlanner" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.DefaultSavePlanner.lookup_object">
-<span class="sig-name descname"><span class="pre">lookup_object</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/default_planner.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultSavePlanner.lookup_object" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">lookup_object</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/default_planner.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultSavePlanner.lookup_object" title="Permalink to this definition">#</a></dt>
 <dd><p>Extension from the planner interface to make it easy to extend the default planner.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5717,7 +5717,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.DefaultSavePlanner.transform_object">
-<span class="sig-name descname"><span class="pre">transform_object</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">write_item</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">object</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/default_planner.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultSavePlanner.transform_object" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">transform_object</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">write_item</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">object</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/default_planner.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultSavePlanner.transform_object" title="Permalink to this definition">#</a></dt>
 <dd><p>Extension from the planner interface to make it easy to extend the default planner.</p>
 <dl class="field-list simple">
 </dl>
@@ -5727,7 +5727,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.DefaultLoadPlanner">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">DefaultLoadPlanner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flatten_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flatten_sharded_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_partial_load</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/default_planner.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultLoadPlanner" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.</span></span><span class="sig-name descname"><span class="pre">DefaultLoadPlanner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flatten_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flatten_sharded_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_partial_load</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/default_planner.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultLoadPlanner" title="Permalink to this definition">#</a></dt>
 <dd><p>DefaultLoadPlanner that adds multiple features on top of LoadPlanner.</p>
 <p>In particular it adds the following:</p>
 <p>flatten_state_dict: Handle state_dict with nested dicts
@@ -5737,7 +5737,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.DefaultLoadPlanner.lookup_tensor">
-<span class="sig-name descname"><span class="pre">lookup_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/default_planner.py#L379"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultLoadPlanner.lookup_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">lookup_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/default_planner.py#L379"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultLoadPlanner.lookup_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Extension from the planner interface to make it easy to extend the default planner.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5748,7 +5748,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.DefaultLoadPlanner.transform_tensor">
-<span class="sig-name descname"><span class="pre">transform_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/default_planner.py#L383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultLoadPlanner.transform_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">transform_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">read_item</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/default_planner.py#L383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.DefaultLoadPlanner.transform_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Extension from the planner interface to make it easy to extend the default planner.</p>
 <dl class="field-list simple">
 </dl>
@@ -5764,7 +5764,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 <p>Note that this feature is experimental, and API signatures might change in the future.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict.get_state_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">get_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizers</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">submodules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict.py#L1111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.get_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">get_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizers</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">submodules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict.py#L1111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.get_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the model state_dict and optimizers state_dict.</p>
 <p><code class="docutils literal notranslate"><span class="pre">get_state_dict</span></code> can process any module that is parallelized by PyTorch
 FSDP/fully_shard, DDP/replicate, tensor_parallel/parallelize_module, and any
@@ -5833,7 +5833,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict.get_model_state_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">get_model_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">submodules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict.py#L1029"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.get_model_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">get_model_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">submodules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict.py#L1029"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.get_model_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the model state_dict of <code class="docutils literal notranslate"><span class="pre">model</span></code>.</p>
 <p>See <code class="docutils literal notranslate"><span class="pre">get_state_dict</span></code> for the detail usage.</p>
 <dl class="field-list simple">
@@ -5858,7 +5858,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict.get_optimizer_state_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">get_optimizer_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizers</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">submodules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict.py#L1066"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.get_optimizer_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">get_optimizer_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizers</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">submodules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict.py#L1066"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.get_optimizer_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the combined state_dict for optimizers.</p>
 <p>See <code class="docutils literal notranslate"><span class="pre">get_state_dict</span></code> for the detail usage.</p>
 <dl class="field-list simple">
@@ -5884,7 +5884,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict.set_state_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">set_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizers</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict.py#L1317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.set_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">set_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizers</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict.py#L1317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.set_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the model state_dict and optimizers state_dict.</p>
 <p>The counterpart of <code class="docutils literal notranslate"><span class="pre">get_state_dict</span></code> to set the state_dict to the model and
 optimizers.  The given <code class="docutils literal notranslate"><span class="pre">model_state_dict</span></code> and <code class="docutils literal notranslate"><span class="pre">optim_state_dict</span></code> do not
@@ -5930,7 +5930,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict.set_model_state_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">set_model_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict.py#L1235"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.set_model_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">set_model_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict.py#L1235"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.set_model_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the model state_dict.</p>
 <p>The counterpart of <code class="docutils literal notranslate"><span class="pre">get_model_state_dict</span></code> to set the state_dict to the
 model. See <code class="docutils literal notranslate"><span class="pre">set_state_dict</span></code> for the detail usage.</p>
@@ -5963,7 +5963,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict.set_optimizer_state_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">set_optimizer_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict.py#L1274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.set_optimizer_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">set_optimizer_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict.py#L1274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.set_optimizer_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizers state_dict.</p>
 <p>The counterpart of <code class="docutils literal notranslate"><span class="pre">get_optimizer_state_dict</span></code> to set the state_dict to the
 optimizers. See <code class="docutils literal notranslate"><span class="pre">set_state_dict</span></code> for the detail usage.</p>
@@ -5995,7 +5995,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.state_dict.StateDictOptions">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">StateDictOptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">full_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cpu_offload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_frozen_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_submodule_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">broadcast_from_rank0</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flatten_optimizer_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dsd_fqn_modifiers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'_fqn_modifiers'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/state_dict.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.StateDictOptions" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.state_dict.</span></span><span class="sig-name descname"><span class="pre">StateDictOptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">full_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cpu_offload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_frozen_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_submodule_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">broadcast_from_rank0</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flatten_optimizer_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dsd_fqn_modifiers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'_fqn_modifiers'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/state_dict.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.state_dict.StateDictOptions" title="Permalink to this definition">#</a></dt>
 <dd><p>This dataclass specifies how get_state_dict/set_state_dict will work.</p>
 <ul class="simple">
 <li><p><code class="docutils literal notranslate"><span class="pre">full_state_dict</span></code>: if this is set to True, all the tensors in the
@@ -6035,7 +6035,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 <p>For users which are used to using and sharing models in the <code class="docutils literal notranslate"><span class="pre">torch.save</span></code> format, the following methods are provided which provide offline utilities for converting betweeing formats.</p>
 <span class="target" id="module-torch.distributed.checkpoint.format_utils"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.dcp_to_torch_save">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.format_utils.</span></span><span class="sig-name descname"><span class="pre">dcp_to_torch_save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dcp_checkpoint_dir</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">torch_save_path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.dcp_to_torch_save" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.format_utils.</span></span><span class="sig-name descname"><span class="pre">dcp_to_torch_save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dcp_checkpoint_dir</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">torch_save_path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.dcp_to_torch_save" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a directory containing a DCP checkpoint, this function will convert it into a
 Torch save file.</p>
 <dl class="field-list simple">
@@ -6054,7 +6054,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.torch_save_to_dcp">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.format_utils.</span></span><span class="sig-name descname"><span class="pre">torch_save_to_dcp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">torch_save_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dcp_checkpoint_dir</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.torch_save_to_dcp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.format_utils.</span></span><span class="sig-name descname"><span class="pre">torch_save_to_dcp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">torch_save_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dcp_checkpoint_dir</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.torch_save_to_dcp" title="Permalink to this definition">#</a></dt>
 <dd><p>Given the location of a torch save file, converts it into a DCP checkpoint.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -6073,7 +6073,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 <p>The following classes can also be utilized for online loading and resharding of models from the torch.save format.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.format_utils.</span></span><span class="sig-name descname"><span class="pre">BroadcastingTorchSaveReader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">coordinator_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.format_utils.</span></span><span class="sig-name descname"><span class="pre">BroadcastingTorchSaveReader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">coordinator_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader" title="Permalink to this definition">#</a></dt>
 <dd><p>StorageReader for reading a Torch Save file. This reader will read the entire checkpoint
 on the coordinator rank, and then broadcast and shard each tensor to all ranks.</p>
 <p>. N.B. Intended to be used with DynamicMetaLoadPlanner</p>
@@ -6094,7 +6094,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.prepare_global_plan">
-<span class="sig-name descname"><span class="pre">prepare_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">global_plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.prepare_global_plan" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prepare_global_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">global_plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.prepare_global_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Implementation of the StorageReader method</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -6105,7 +6105,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.prepare_local_plan">
-<span class="sig-name descname"><span class="pre">prepare_local_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L132"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.prepare_local_plan" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prepare_local_plan</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L132"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.prepare_local_plan" title="Permalink to this definition">#</a></dt>
 <dd><p>Implementation of the StorageReader method</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -6116,7 +6116,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.read_data">
-<span class="sig-name descname"><span class="pre">read_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.read_data" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">read_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">plan</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">planner</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.read_data" title="Permalink to this definition">#</a></dt>
 <dd><p>Reads torch save data on the coordinator rank, and broadcast afterwards
 this incurrs a communication cost, but avoids having to load
 the entire checkpoint on each rank, hopefully preventing OOM issues</p>
@@ -6129,7 +6129,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.read_metadata">
-<span class="sig-name descname"><span class="pre">read_metadata</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L67"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.read_metadata" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">read_metadata</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L67"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.read_metadata" title="Permalink to this definition">#</a></dt>
 <dd><p>Extends the default StorageReader to support building the metadata file</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -6140,7 +6140,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.reset">
-<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.reset" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.reset" title="Permalink to this definition">#</a></dt>
 <dd><p>Implementation of the StorageReader method</p>
 <dl class="field-list simple">
 </dl>
@@ -6148,7 +6148,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.set_up_storage_reader">
-<span class="sig-name descname"><span class="pre">set_up_storage_reader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.set_up_storage_reader" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_up_storage_reader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metadata</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.set_up_storage_reader" title="Permalink to this definition">#</a></dt>
 <dd><p>Implementation of the StorageReader method</p>
 <dl class="field-list simple">
 </dl>
@@ -6156,7 +6156,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.validate_checkpoint_id">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">validate_checkpoint_id</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.validate_checkpoint_id" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">validate_checkpoint_id</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">checkpoint_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.BroadcastingTorchSaveReader.validate_checkpoint_id" title="Permalink to this definition">#</a></dt>
 <dd><p>Implementation of the StorageReader method</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -6169,7 +6169,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.DynamicMetaLoadPlanner">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.format_utils.</span></span><span class="sig-name descname"><span class="pre">DynamicMetaLoadPlanner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flatten_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flatten_sharded_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_partial_load</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L150"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.DynamicMetaLoadPlanner" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.checkpoint.format_utils.</span></span><span class="sig-name descname"><span class="pre">DynamicMetaLoadPlanner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flatten_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flatten_sharded_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_partial_load</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L150"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.DynamicMetaLoadPlanner" title="Permalink to this definition">#</a></dt>
 <dd><p>Extension of DefaultLoadPlanner, which creates a new Metadata object based on the passed in state dict,
 avoiding the need to read metadata from disk. This is useful when reading formats which don’t have a
 metadata file, like Torch Save files.</p>
@@ -6191,7 +6191,7 @@ <h2>Additional resources:<a class="headerlink" href="#additional-resources" titl
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.checkpoint.format_utils.DynamicMetaLoadPlanner.set_up_planner">
-<span class="sig-name descname"><span class="pre">set_up_planner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/checkpoint/format_utils.py#L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.DynamicMetaLoadPlanner.set_up_planner" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_up_planner</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_coordinator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/checkpoint/format_utils.py#L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.checkpoint.format_utils.DynamicMetaLoadPlanner.set_up_planner" title="Permalink to this definition">#</a></dt>
 <dd><p>Setups of the planner, extnding default behavior by creating the Metadata object from the state dict</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/distributed.fsdp.fully_shard.html b/2.9/distributed.fsdp.fully_shard.html
index 415ecd40e18..482c0aaae44 100644
--- a/2.9/distributed.fsdp.fully_shard.html
+++ b/2.9/distributed.fsdp.fully_shard.html
@@ -4470,7 +4470,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 <p>The frontend API is <code class="docutils literal notranslate"><span class="pre">fully_shard</span></code> that can be called on a <code class="docutils literal notranslate"><span class="pre">module</span></code>:</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.fully_shard">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">fully_shard</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reshard_after_forward</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shard_placement_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mp_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">MixedPrecisionPolicy(param_dtype=None,</span> <span class="pre">reduce_dtype=None,</span> <span class="pre">output_dtype=None,</span> <span class="pre">cast_forward_inputs=True)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offload_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">OffloadPolicy()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignored_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.fully_shard" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">fully_shard</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reshard_after_forward</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shard_placement_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mp_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">MixedPrecisionPolicy(param_dtype=None,</span> <span class="pre">reduce_dtype=None,</span> <span class="pre">output_dtype=None,</span> <span class="pre">cast_forward_inputs=True)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offload_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">OffloadPolicy()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignored_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.fully_shard" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply fully sharded data parallelism (FSDP) to <code class="docutils literal notranslate"><span class="pre">module</span></code>, where FSDP
 shards module parameters, gradients, and optimizer states across data
 parallel workers to save memory at the cost of communication.</p>
@@ -4573,7 +4573,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">FSDPModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule" title="Permalink to this definition">#</a></dt>
 <dd><dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.reshard">
-<span class="sig-name descname"><span class="pre">reshard</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.reshard" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reshard</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.reshard" title="Permalink to this definition">#</a></dt>
 <dd><p>Reshards the module’s parameters, freeing the unsharded parameters if
 they are allocated and registering the sharded parameters to the
 module. This method is <em>not</em> recursive.</p>
@@ -4583,7 +4583,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_all_reduce_hook">
-<span class="sig-name descname"><span class="pre">set_all_reduce_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L484"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_all_reduce_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_all_reduce_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L484"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_all_reduce_hook" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
 <dd class="field-odd"><ul class="simple">
@@ -4602,7 +4602,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_allocate_memory_from_process_group_for_comm">
-<span class="sig-name descname"><span class="pre">set_allocate_memory_from_process_group_for_comm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_allocate_memory_from_process_group_for_comm" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_allocate_memory_from_process_group_for_comm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_allocate_memory_from_process_group_for_comm" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether the temporary staging buffers used to send and receive data
 over collective communications should be allocated using the custom
 optimized allocator provided by the ProcessGroup itself (if any). This
@@ -4622,7 +4622,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_custom_all_gather">
-<span class="sig-name descname"><span class="pre">set_custom_all_gather</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">comm</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L458"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_custom_all_gather" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_custom_all_gather</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">comm</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L458"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_custom_all_gather" title="Permalink to this definition">#</a></dt>
 <dd><p>Overrides the default <code class="docutils literal notranslate"><span class="pre">all_gather</span></code> communication behavior,
 to have better control over the communication and memory usage.
 See <cite>Comm</cite> and <cite>ReduceScatter</cite> for details.</p>
@@ -4635,7 +4635,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_custom_reduce_scatter">
-<span class="sig-name descname"><span class="pre">set_custom_reduce_scatter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">comm</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L471"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_custom_reduce_scatter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_custom_reduce_scatter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">comm</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L471"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_custom_reduce_scatter" title="Permalink to this definition">#</a></dt>
 <dd><p>Overrides the default <code class="docutils literal notranslate"><span class="pre">reduce_scatter</span></code> communication behavior,
 to have better control over the communication and memory usage.
 See <cite>Comm</cite> and <cite>ReduceScatter</cite> for details.</p>
@@ -4648,7 +4648,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_force_sum_reduction_for_comms">
-<span class="sig-name descname"><span class="pre">set_force_sum_reduction_for_comms</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L546"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_force_sum_reduction_for_comms" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_force_sum_reduction_for_comms</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L546"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_force_sum_reduction_for_comms" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether to require the low-level collective communication
 primitives to exclusively use “sum”-type reductions, even if it comes
 at the cost of separate additional pre- or post-scaling operations.
@@ -4667,7 +4667,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_gradient_divide_factor">
-<span class="sig-name descname"><span class="pre">set_gradient_divide_factor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L533"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_gradient_divide_factor" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_gradient_divide_factor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L533"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_gradient_divide_factor" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets a custom divide factor for the gradient reduction. This might use
 a custom reduce op using NCCL’s PreMulSum, which allows multiplying by
 the factor before reduction.</p>
@@ -4680,7 +4680,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_is_last_backward">
-<span class="sig-name descname"><span class="pre">set_is_last_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">is_last_backward</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L311"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_is_last_backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_is_last_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">is_last_backward</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L311"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_is_last_backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether the next backward is the last one. On the last backward,
 FSDP waits on pending gradient reduction and clears internal data
 data structures for backward prefetching. This can be useful for
@@ -4691,7 +4691,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_modules_to_backward_prefetch">
-<span class="sig-name descname"><span class="pre">set_modules_to_backward_prefetch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L438"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_modules_to_backward_prefetch" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_modules_to_backward_prefetch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L438"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_modules_to_backward_prefetch" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the FSDP modules for which this FSDP module should explicitly
 prefetch all-gathers in backward. This overrides the default backward
 pretching implementation that prefetches the next FSDP module based on
@@ -4709,7 +4709,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_modules_to_forward_prefetch">
-<span class="sig-name descname"><span class="pre">set_modules_to_forward_prefetch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L418"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_modules_to_forward_prefetch" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_modules_to_forward_prefetch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L418"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_modules_to_forward_prefetch" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the FSDP modules for which this FSDP module should explicitly
 prefetch all-gathers in forward. The prefetching runs after this
 module’s all-gather copy-out.</p>
@@ -4727,7 +4727,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_post_optim_event">
-<span class="sig-name descname"><span class="pre">set_post_optim_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L509"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_post_optim_event" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_post_optim_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L509"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_post_optim_event" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets a post-optimizer-step event for the root FSDP module to wait the
 all-gather streams on.</p>
 <p>By default, the root FSDP module waits the all-gather streams on the
@@ -4747,7 +4747,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_reduce_scatter_divide_factor">
-<span class="sig-name descname"><span class="pre">set_reduce_scatter_divide_factor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_reduce_scatter_divide_factor" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_reduce_scatter_divide_factor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_reduce_scatter_divide_factor" title="Permalink to this definition">#</a></dt>
 <dd><p>Use <a class="reference internal" href="#torch.distributed.fsdp.FSDPModule.set_gradient_divide_factor" title="torch.distributed.fsdp.FSDPModule.set_gradient_divide_factor"><code class="xref py py-meth docutils literal notranslate"><span class="pre">set_gradient_divide_factor()</span></code></a> instead</p>
 <dl class="field-list simple">
 </dl>
@@ -4755,7 +4755,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_requires_all_reduce">
-<span class="sig-name descname"><span class="pre">set_requires_all_reduce</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_all_reduce</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_requires_all_reduce" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_requires_all_reduce</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_all_reduce</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_requires_all_reduce" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets if the module should all-reduce gradients. This can be used to
 implement gradient accumulation with only reduce-scatter but not
 all-reduce for HSDP.</p>
@@ -4765,7 +4765,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_requires_gradient_sync">
-<span class="sig-name descname"><span class="pre">set_requires_gradient_sync</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_gradient_sync</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_requires_gradient_sync" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_requires_gradient_sync</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_gradient_sync</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_requires_gradient_sync" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets if the module should sync gradients. This can be used to implement
 gradient accumulation <em>without communication</em>. For HSDP, this controls
 both reduce-scatter and all-reduce together. This is the equivalence of
@@ -4784,7 +4784,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_reshard_after_backward">
-<span class="sig-name descname"><span class="pre">set_reshard_after_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reshard_after_backward</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_reshard_after_backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_reshard_after_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reshard_after_backward</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_reshard_after_backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets if the module should reshard parameters after backward. This can
 be used during gradient accumulation to trade off higher memory for
 reduced communication since the unsharded parameters do not need to be
@@ -4803,7 +4803,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_reshard_after_forward">
-<span class="sig-name descname"><span class="pre">set_reshard_after_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reshard_after_forward</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L361"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_reshard_after_forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_reshard_after_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reshard_after_forward</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L361"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_reshard_after_forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets if the module should reshard parameters after forward. This can be
 used to change the <code class="docutils literal notranslate"><span class="pre">reshard_after_forward</span></code> FSDP arg at runtime. For
 example, this can be used to set the FSDP root module’s value to
@@ -4824,7 +4824,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.set_unshard_in_backward">
-<span class="sig-name descname"><span class="pre">set_unshard_in_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">unshard_in_backward</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L567"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_unshard_in_backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_unshard_in_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">unshard_in_backward</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L567"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.set_unshard_in_backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether the FSDP module’s parameters need to be unsharded in
 backward. This can be used in expert cases when the user knows that all
 parameters in this FSDP module’s parameter group are not needed for
@@ -4835,7 +4835,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FSDPModule.unshard">
-<span class="sig-name descname"><span class="pre">unshard</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L282"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.unshard" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">unshard</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L282"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FSDPModule.unshard" title="Permalink to this definition">#</a></dt>
 <dd><p>Unshards the module’s parameters by allocating memory and all-gathering
 the parameters. This method is <em>not</em> recursive. The unshard follows the
 <a class="reference internal" href="#torch.distributed.fsdp.MixedPrecisionPolicy" title="torch.distributed.fsdp.MixedPrecisionPolicy"><code class="xref py py-class docutils literal notranslate"><span class="pre">MixedPrecisionPolicy</span></code></a>, so it will all-gather following
@@ -4868,7 +4868,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 <dd><p>A handle to wait on a <a class="reference internal" href="#torch.distributed.fsdp.FSDPModule.unshard" title="torch.distributed.fsdp.FSDPModule.unshard"><code class="xref py py-meth docutils literal notranslate"><span class="pre">FSDPModule.unshard()</span></code></a> op.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.UnshardHandle.wait">
-<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L643"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.UnshardHandle.wait" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L643"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.UnshardHandle.wait" title="Permalink to this definition">#</a></dt>
 <dd><p>Waits on the unshard op. This ensures that the current stream can use
 the unsharded parameters, which are now registered to the module.</p>
 <dl class="field-list simple">
@@ -4879,7 +4879,7 @@ <h2>PyTorch FSDP2 (<code class="docutils literal notranslate"><span class="pre">
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.register_fsdp_forward_method">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">register_fsdp_forward_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">method_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L662"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.register_fsdp_forward_method" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">register_fsdp_forward_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">method_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/_fully_shard/_fully_shard.py#L662"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.register_fsdp_forward_method" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a method on <code class="docutils literal notranslate"><span class="pre">module</span></code> to be considered a forward method for
 FSDP.</p>
 <p>FSDP all-gathers parameters pre-forward and optionally frees parameters
diff --git a/2.9/distributed.html b/2.9/distributed.html
index 07f88c4c66c..eba0d2e9bab 100644
--- a/2.9/distributed.html
+++ b/2.9/distributed.html
@@ -4688,7 +4688,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/__init__.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/__init__.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return <code class="docutils literal notranslate"><span class="pre">True</span></code> if the distributed package is available.</p>
 <p>Otherwise,
 <code class="docutils literal notranslate"><span class="pre">torch.distributed</span></code> does not expose any other APIs. Currently,
@@ -4705,7 +4705,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.init_process_group">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">init_process_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">store</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pg_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1541"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.init_process_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">init_process_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">store</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pg_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1541"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.init_process_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize the default distributed process group.</p>
 <p>This will also initialize the distributed package.</p>
 <dl class="simple">
@@ -4799,7 +4799,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.device_mesh.init_device_mesh">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.device_mesh.</span></span><span class="sig-name descname"><span class="pre">init_device_mesh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh_shape</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh_dim_names</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/device_mesh.py#L1076"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.init_device_mesh" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.device_mesh.</span></span><span class="sig-name descname"><span class="pre">init_device_mesh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh_shape</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh_dim_names</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/device_mesh.py#L1076"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.init_device_mesh" title="Permalink to this definition">#</a></dt>
 <dd><p>Initializes a <cite>DeviceMesh</cite> based on <cite>device_type</cite>, <cite>mesh_shape</cite>, and <cite>mesh_dim_names</cite> parameters.</p>
 <p>This creates a DeviceMesh with an n-dimensional array layout, where <cite>n</cite> is the length of <cite>mesh_shape</cite>.
 If <cite>mesh_dim_names</cite> is provided, each dimension is labeled as <cite>mesh_dim_names[i]</cite>.</p>
@@ -4849,7 +4849,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.is_initialized">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_initialized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_initialized" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_initialized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_initialized" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the default process group has been initialized.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4860,7 +4860,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.is_mpi_available">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_mpi_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1229"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_mpi_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_mpi_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1229"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_mpi_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the MPI backend is available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4871,7 +4871,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.is_nccl_available">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_nccl_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_nccl_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_nccl_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_nccl_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the NCCL backend is available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4882,7 +4882,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.is_gloo_available">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_gloo_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1239"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_gloo_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_gloo_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1239"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_gloo_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the Gloo backend is available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4893,7 +4893,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.distributed_c10d.is_xccl_available">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.distributed_c10d.</span></span><span class="sig-name descname"><span class="pre">is_xccl_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.distributed_c10d.is_xccl_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.distributed_c10d.</span></span><span class="sig-name descname"><span class="pre">is_xccl_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.distributed_c10d.is_xccl_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the XCCL backend is available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4904,7 +4904,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.is_torchelastic_launched">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_torchelastic_launched</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1279"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_torchelastic_launched" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">is_torchelastic_launched</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1279"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.is_torchelastic_launched" title="Permalink to this definition">#</a></dt>
 <dd><p>Check whether this process was launched with <code class="docutils literal notranslate"><span class="pre">torch.distributed.elastic</span></code> (aka torchelastic).</p>
 <p>The existence of <code class="docutils literal notranslate"><span class="pre">TORCHELASTIC_RUN_ID</span></code> environment
 variable is used as a proxy to determine whether the current process
@@ -4920,7 +4920,7 @@ <h2>Initialization<a class="headerlink" href="#initialization" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.get_default_backend_for_device">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_default_backend_for_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_default_backend_for_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_default_backend_for_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_default_backend_for_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the default backend for the given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5024,7 +5024,7 @@ <h2>Post-Initialization<a class="headerlink" href="#post-initialization" title="
 check whether the process group has already been initialized use <a class="reference internal" href="#torch.distributed.is_initialized" title="torch.distributed.is_initialized"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.distributed.is_initialized()</span></code></a>.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.Backend">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">Backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.Backend" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">Backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.Backend" title="Permalink to this definition">#</a></dt>
 <dd><p>An enum-like class for backends.</p>
 <p>Available backends: GLOO, NCCL, UCC, MPI, XCCL, and other registered backends.</p>
 <p>The values of this class are lowercase strings, e.g., <code class="docutils literal notranslate"><span class="pre">&quot;gloo&quot;</span></code>. They can
@@ -5043,7 +5043,7 @@ <h2>Post-Initialization<a class="headerlink" href="#post-initialization" title="
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.Backend.register_backend">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">register_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extended_api</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.Backend.register_backend" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">register_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extended_api</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.Backend.register_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a new backend with the given name and instantiating function.</p>
 <p>This class method is used by 3rd party <code class="docutils literal notranslate"><span class="pre">ProcessGroup</span></code> extension to
 register new backends.</p>
@@ -5076,7 +5076,7 @@ <h2>Post-Initialization<a class="headerlink" href="#post-initialization" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.get_backend">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1351"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_backend" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1351"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the backend of the given process group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5095,7 +5095,7 @@ <h2>Post-Initialization<a class="headerlink" href="#post-initialization" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.get_rank">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_rank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2331"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_rank" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_rank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2331"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_rank" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the rank of the current process in the provided <code class="docutils literal notranslate"><span class="pre">group</span></code>, default otherwise.</p>
 <p>Rank is a unique identifier assigned to each process within a distributed
 process group. They are always consecutive integers ranging from 0 to
@@ -5117,7 +5117,7 @@ <h2>Post-Initialization<a class="headerlink" href="#post-initialization" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.get_world_size">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_world_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_world_size" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_world_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_world_size" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the number of processes in the current process group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5173,7 +5173,7 @@ <h2>Groups<a class="headerlink" href="#groups" title="Permalink to this heading"
 (collectives are distributed functions to exchange information in certain well-known programming patterns).</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.new_group">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">new_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ranks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pg_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_synchronization</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_desc</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L5198"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.new_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">new_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ranks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pg_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_synchronization</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_desc</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L5198"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.new_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a new distributed group.</p>
 <p>This function requires that all processes in the main group (i.e. all
 processes that are part of the distributed job) enter this function, even
@@ -5242,7 +5242,7 @@ <h2>Groups<a class="headerlink" href="#groups" title="Permalink to this heading"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.get_group_rank">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_group_rank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_rank</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1011"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_group_rank" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_group_rank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_rank</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1011"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_group_rank" title="Permalink to this definition">#</a></dt>
 <dd><p>Translate a global rank into a group rank.</p>
 <p><code class="docutils literal notranslate"><span class="pre">global_rank</span></code> must be part of <code class="docutils literal notranslate"><span class="pre">group</span></code> otherwise this raises RuntimeError.</p>
 <dl class="field-list simple">
@@ -5264,7 +5264,7 @@ <h2>Groups<a class="headerlink" href="#groups" title="Permalink to this heading"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.get_global_rank">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_global_rank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_rank</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1039"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_global_rank" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_global_rank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_rank</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1039"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_global_rank" title="Permalink to this definition">#</a></dt>
 <dd><p>Translate a group rank into a global rank.</p>
 <p><code class="docutils literal notranslate"><span class="pre">group_rank</span></code> must be part of <cite>group</cite> otherwise this raises RuntimeError.</p>
 <dl class="field-list simple">
@@ -5286,7 +5286,7 @@ <h2>Groups<a class="headerlink" href="#groups" title="Permalink to this heading"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.get_process_group_ranks">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_process_group_ranks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L1077"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_process_group_ranks" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">get_process_group_ranks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L1077"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.get_process_group_ranks" title="Permalink to this definition">#</a></dt>
 <dd><p>Get all ranks associated with <code class="docutils literal notranslate"><span class="pre">group</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5312,7 +5312,7 @@ <h2>DeviceMesh<a class="headerlink" href="#devicemesh" title="Permalink to this
 used to create new DeviceMesh, with a mesh shape describing the device topology.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.device_mesh.DeviceMesh">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.device_mesh.</span></span><span class="sig-name descname"><span class="pre">DeviceMesh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh_dim_names</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_init_backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/device_mesh.py#L395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.device_mesh.</span></span><span class="sig-name descname"><span class="pre">DeviceMesh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh_dim_names</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_init_backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/device_mesh.py#L395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh" title="Permalink to this definition">#</a></dt>
 <dd><p>DeviceMesh represents a mesh of devices, where layout of devices could be
 represented as a n-d dimension array, and each value of the n-d dimensional
 array is the global id of the default process group ranks.</p>
@@ -5360,7 +5360,7 @@ <h2>DeviceMesh<a class="headerlink" href="#devicemesh" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.device_mesh.DeviceMesh.from_group">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh_dim_names</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/device_mesh.py#L846"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.from_group" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mesh_dim_names</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/device_mesh.py#L846"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.from_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Constructs a <a class="reference internal" href="#torch.distributed.device_mesh.DeviceMesh" title="torch.distributed.device_mesh.DeviceMesh"><code class="xref py py-class docutils literal notranslate"><span class="pre">DeviceMesh</span></code></a> with <code class="docutils literal notranslate"><span class="pre">device_type</span></code> from an
 existing <code class="xref py py-class docutils literal notranslate"><span class="pre">ProcessGroup</span></code> or a list of existing <code class="xref py py-class docutils literal notranslate"><span class="pre">ProcessGroup</span></code>.</p>
 <p>The constructed device mesh has number of dimensions equal to the
@@ -5401,7 +5401,7 @@ <h2>DeviceMesh<a class="headerlink" href="#devicemesh" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.device_mesh.DeviceMesh.get_all_groups">
-<span class="sig-name descname"><span class="pre">get_all_groups</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/device_mesh.py#L837"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_all_groups" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_all_groups</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/device_mesh.py#L837"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_all_groups" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a list of ProcessGroups for all mesh dimensions.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5415,7 +5415,7 @@ <h2>DeviceMesh<a class="headerlink" href="#devicemesh" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.device_mesh.DeviceMesh.get_coordinate">
-<span class="sig-name descname"><span class="pre">get_coordinate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/device_mesh.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_coordinate" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_coordinate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/device_mesh.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_coordinate" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the relative indices of this rank relative to all
 dimensions of the mesh. If this rank is not part of the mesh, return None.</p>
 <dl class="field-list simple">
@@ -5427,7 +5427,7 @@ <h2>DeviceMesh<a class="headerlink" href="#devicemesh" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.device_mesh.DeviceMesh.get_group">
-<span class="sig-name descname"><span class="pre">get_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mesh_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/device_mesh.py#L792"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mesh_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/device_mesh.py#L792"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the single ProcessGroup specified by mesh_dim, or, if mesh_dim is not specified and the
 DeviceMesh is 1-dimensional, returns the only ProcessGroup in the mesh.</p>
 <dl class="field-list simple">
@@ -5448,7 +5448,7 @@ <h2>DeviceMesh<a class="headerlink" href="#devicemesh" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.device_mesh.DeviceMesh.get_local_rank">
-<span class="sig-name descname"><span class="pre">get_local_rank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mesh_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/device_mesh.py#L954"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_local_rank" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_local_rank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mesh_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/device_mesh.py#L954"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_local_rank" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the local rank of the given mesh_dim of the DeviceMesh.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5484,7 +5484,7 @@ <h2>DeviceMesh<a class="headerlink" href="#devicemesh" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.device_mesh.DeviceMesh.get_rank">
-<span class="sig-name descname"><span class="pre">get_rank</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/device_mesh.py#L948"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_rank" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_rank</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/device_mesh.py#L948"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.device_mesh.DeviceMesh.get_rank" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the current global rank.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5500,7 +5500,7 @@ <h2>DeviceMesh<a class="headerlink" href="#devicemesh" title="Permalink to this
 <h2>Point-to-point communication<a class="headerlink" href="#point-to-point-communication" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.send">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">send</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2467"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.send" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">send</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2467"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.send" title="Permalink to this definition">#</a></dt>
 <dd><p>Send a tensor synchronously.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -5523,7 +5523,7 @@ <h2>Point-to-point communication<a class="headerlink" href="#point-to-point-comm
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.recv">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">recv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2499"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.recv" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">recv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2499"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.recv" title="Permalink to this definition">#</a></dt>
 <dd><p>Receives a tensor synchronously.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -5561,7 +5561,7 @@ <h2>Point-to-point communication<a class="headerlink" href="#point-to-point-comm
 </ul>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.isend">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">isend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.isend" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">isend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.isend" title="Permalink to this definition">#</a></dt>
 <dd><p>Send a tensor asynchronously.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -5596,7 +5596,7 @@ <h2>Point-to-point communication<a class="headerlink" href="#point-to-point-comm
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.irecv">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">irecv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.irecv" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">irecv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.irecv" title="Permalink to this definition">#</a></dt>
 <dd><p>Receives a tensor asynchronously.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -5627,7 +5627,7 @@ <h2>Point-to-point communication<a class="headerlink" href="#point-to-point-comm
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.send_object_list">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">send_object_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_batch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3328"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.send_object_list" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">send_object_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_batch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3328"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.send_object_list" title="Permalink to this definition">#</a></dt>
 <dd><p>Sends picklable objects in <code class="docutils literal notranslate"><span class="pre">object_list</span></code> synchronously.</p>
 <p>Similar to <a class="reference internal" href="#torch.distributed.send" title="torch.distributed.send"><code class="xref py py-func docutils literal notranslate"><span class="pre">send()</span></code></a>, but Python objects can be passed in.
 Note that all objects in <code class="docutils literal notranslate"><span class="pre">object_list</span></code> must be picklable in order to be
@@ -5705,7 +5705,7 @@ <h2>Point-to-point communication<a class="headerlink" href="#point-to-point-comm
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.recv_object_list">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">recv_object_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_batch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.recv_object_list" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">recv_object_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_batch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.recv_object_list" title="Permalink to this definition">#</a></dt>
 <dd><p>Receives picklable objects in <code class="docutils literal notranslate"><span class="pre">object_list</span></code> synchronously.</p>
 <p>Similar to <a class="reference internal" href="#torch.distributed.recv" title="torch.distributed.recv"><code class="xref py py-func docutils literal notranslate"><span class="pre">recv()</span></code></a>, but can receive Python objects.</p>
 <dl class="field-list simple">
@@ -5781,7 +5781,7 @@ <h2>Point-to-point communication<a class="headerlink" href="#point-to-point-comm
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.batch_isend_irecv">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">batch_isend_irecv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p2p_op_list</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2714"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.batch_isend_irecv" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">batch_isend_irecv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p2p_op_list</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2714"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.batch_isend_irecv" title="Permalink to this definition">#</a></dt>
 <dd><p>Send or Receive a batch of tensors asynchronously and return a list of requests.</p>
 <p>Process each of the operations in <code class="docutils literal notranslate"><span class="pre">p2p_op_list</span></code> and return the corresponding
 requests. NCCL, Gloo, and UCC backend are currently supported.</p>
@@ -5830,7 +5830,7 @@ <h2>Point-to-point communication<a class="headerlink" href="#point-to-point-comm
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.P2POp">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">P2POp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">peer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_peer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.P2POp" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">P2POp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">peer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_peer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.P2POp" title="Permalink to this definition">#</a></dt>
 <dd><p>A class to build point-to-point operations for <code class="docutils literal notranslate"><span class="pre">batch_isend_irecv</span></code>.</p>
 <p>This class builds the type of P2P operation, communication buffer, peer rank,
 Process Group, and tag. Instances of this class will be passed to
@@ -5905,7 +5905,7 @@ <h2>Synchronous and asynchronous collective operations<a class="headerlink" href
 <h2>Collective functions<a class="headerlink" href="#collective-functions" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.broadcast">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">broadcast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2793"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.broadcast" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">broadcast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2793"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.broadcast" title="Permalink to this definition">#</a></dt>
 <dd><p>Broadcasts the tensor to the whole group.</p>
 <p><code class="docutils literal notranslate"><span class="pre">tensor</span></code> must have the same number of elements in all processes
 participating in the collective.</p>
@@ -5931,7 +5931,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.broadcast_object_list">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">broadcast_object_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.broadcast_object_list" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">broadcast_object_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.broadcast_object_list" title="Permalink to this definition">#</a></dt>
 <dd><p>Broadcasts picklable objects in <code class="docutils literal notranslate"><span class="pre">object_list</span></code> to the whole group.</p>
 <p>Similar to <a class="reference internal" href="#torch.distributed.broadcast" title="torch.distributed.broadcast"><code class="xref py py-func docutils literal notranslate"><span class="pre">broadcast()</span></code></a>, but Python objects can be passed in.
 Note that all objects in <code class="docutils literal notranslate"><span class="pre">object_list</span></code> must be picklable in order to be
@@ -6012,7 +6012,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.all_reduce">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_reduce</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op=&lt;RedOpType.SUM:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L2845"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_reduce" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_reduce</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op=&lt;RedOpType.SUM:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L2845"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_reduce" title="Permalink to this definition">#</a></dt>
 <dd><p>Reduces the tensor data across all machines in a way that all get the final result.</p>
 <p>After the call <code class="docutils literal notranslate"><span class="pre">tensor</span></code> is going to be bitwise identical in all processes.</p>
 <p>Complex tensors are supported.</p>
@@ -6066,7 +6066,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.reduce">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">reduce</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op=&lt;RedOpType.SUM:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3015"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.reduce" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">reduce</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op=&lt;RedOpType.SUM:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3015"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.reduce" title="Permalink to this definition">#</a></dt>
 <dd><p>Reduces the tensor data across all machines.</p>
 <p>Only the process with rank <code class="docutils literal notranslate"><span class="pre">dst</span></code> is going to receive the final result.</p>
 <dl class="field-list simple">
@@ -6094,7 +6094,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.all_gather">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_gather</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_gather" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_gather</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_gather" title="Permalink to this definition">#</a></dt>
 <dd><p>Gathers tensors from the whole group in a list.</p>
 <p>Complex and uneven sized tensors are supported.</p>
 <dl class="field-list simple">
@@ -6158,7 +6158,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.all_gather_into_tensor">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_gather_into_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3953"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_gather_into_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_gather_into_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3953"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_gather_into_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Gather tensors from all ranks and put them in a single output tensor.</p>
 <p>This function requires all tensors to be the same size on each process.</p>
 <dl class="field-list simple">
@@ -6213,7 +6213,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.all_gather_object">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_gather_object</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_gather_object" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_gather_object</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_gather_object" title="Permalink to this definition">#</a></dt>
 <dd><p>Gathers picklable objects from the whole group into a list.</p>
 <p>Similar to <a class="reference internal" href="#torch.distributed.all_gather" title="torch.distributed.all_gather"><code class="xref py py-func docutils literal notranslate"><span class="pre">all_gather()</span></code></a>, but Python objects can be passed in.
 Note that the object must be picklable in order to be gathered.</p>
@@ -6284,7 +6284,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.gather">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">gather</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gather_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L4192"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.gather" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">gather</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gather_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L4192"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.gather" title="Permalink to this definition">#</a></dt>
 <dd><p>Gathers a list of tensors in a single process.</p>
 <p>This function requires all tensors to be the same size on each process.</p>
 <dl class="field-list simple">
@@ -6333,7 +6333,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.gather_object">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">gather_object</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">object_gather_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.gather_object" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">gather_object</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">object_gather_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_dst</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.gather_object" title="Permalink to this definition">#</a></dt>
 <dd><p>Gathers picklable objects from the whole group in a single process.</p>
 <p>Similar to <a class="reference internal" href="#torch.distributed.gather" title="torch.distributed.gather"><code class="xref py py-func docutils literal notranslate"><span class="pre">gather()</span></code></a>, but Python objects can be passed in. Note that the
 object must be picklable in order to be gathered.</p>
@@ -6412,7 +6412,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.scatter">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">scatter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scatter_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L4275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.scatter" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">scatter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scatter_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L4275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.scatter" title="Permalink to this definition">#</a></dt>
 <dd><p>Scatters a list of tensors to all processes in a group.</p>
 <p>Each process will receive exactly one tensor and store its data in the
 <code class="docutils literal notranslate"><span class="pre">tensor</span></code> argument.</p>
@@ -6467,7 +6467,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.scatter_object_list">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">scatter_object_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scatter_object_output_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scatter_object_input_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L3719"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.scatter_object_list" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">scatter_object_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scatter_object_output_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scatter_object_input_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_src</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L3719"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.scatter_object_list" title="Permalink to this definition">#</a></dt>
 <dd><p>Scatters picklable objects in <code class="docutils literal notranslate"><span class="pre">scatter_object_input_list</span></code> to the whole group.</p>
 <p>Similar to <a class="reference internal" href="#torch.distributed.scatter" title="torch.distributed.scatter"><code class="xref py py-func docutils literal notranslate"><span class="pre">scatter()</span></code></a>, but Python objects can be passed in. On
 each rank, the scattered object will be stored as the first element of
@@ -6540,7 +6540,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.reduce_scatter">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">reduce_scatter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op=&lt;RedOpType.SUM:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L4380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.reduce_scatter" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">reduce_scatter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op=&lt;RedOpType.SUM:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L4380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.reduce_scatter" title="Permalink to this definition">#</a></dt>
 <dd><p>Reduces, then scatters a list of tensors to all processes in a group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -6564,7 +6564,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.reduce_scatter_tensor">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">reduce_scatter_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op=&lt;RedOpType.SUM:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L4423"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.reduce_scatter_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">reduce_scatter_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op=&lt;RedOpType.SUM:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L4423"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.reduce_scatter_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Reduces, then scatters a tensor to all ranks in a group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -6620,7 +6620,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.all_to_all_single">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_to_all_single</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_split_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_split_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L4552"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_to_all_single" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_to_all_single</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_split_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_split_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L4552"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_to_all_single" title="Permalink to this definition">#</a></dt>
 <dd><p>Split input tensor and then scatter the split list to all processes in a group.</p>
 <p>Later the received tensors are concatenated from all the processes in the group
 and returned as a single output tensor.</p>
@@ -6720,7 +6720,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.all_to_all">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_to_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_tensor_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_tensor_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L4701"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_to_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">all_to_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_tensor_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_tensor_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L4701"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.all_to_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Scatters list of input tensors to all processes in a group and return gathered list of tensors in output list.</p>
 <p>Complex tensors are supported.</p>
 <dl class="field-list simple">
@@ -6820,7 +6820,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.barrier">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">barrier</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L4823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.barrier" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">barrier</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L4823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.barrier" title="Permalink to this definition">#</a></dt>
 <dd><p>Synchronize all processes.</p>
 <p>This collective blocks processes until the whole group enters this function,
 if async_op is False, or if async work handle is called on wait().</p>
@@ -6854,7 +6854,7 @@ <h2>Collective functions<a class="headerlink" href="#collective-functions" title
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.monitored_barrier">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">monitored_barrier</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wait_all_ranks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/distributed_c10d.py#L4892"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.monitored_barrier" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">monitored_barrier</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wait_all_ranks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/distributed_c10d.py#L4892"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.monitored_barrier" title="Permalink to this definition">#</a></dt>
 <dd><p>Synchronize processes similar to <code class="docutils literal notranslate"><span class="pre">torch.distributed.barrier</span></code>, but consider a configurable timeout.</p>
 <p>It is able to report ranks that did not pass this barrier within the provided timeout.
 Specifically, for non-zero ranks, will block until a send/recv is processed from rank 0.
@@ -8206,7 +8206,7 @@ <h2>Logging<a class="headerlink" href="#logging" title="Permalink to this headin
 <p>If you are running single node training, it may be convenient to interactively breakpoint your script. We offer a way to conveniently breakpoint a single rank:</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.breakpoint">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">breakpoint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout_s</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3600</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/__init__.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.breakpoint" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.</span></span><span class="sig-name descname"><span class="pre">breakpoint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout_s</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3600</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/__init__.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.breakpoint" title="Permalink to this definition">#</a></dt>
 <dd><p>Set a breakpoint, but only on a single rank.  All other ranks will wait for you to be
 done with the breakpoint before continuing.</p>
 <dl class="field-list simple">
diff --git a/2.9/distributed.optim.html b/2.9/distributed.optim.html
index 93dd97fd50b..03af88cac8e 100644
--- a/2.9/distributed.optim.html
+++ b/2.9/distributed.optim.html
@@ -4405,7 +4405,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 apply the gradients on each worker.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.optim.DistributedOptimizer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.optim.</span></span><span class="sig-name descname"><span class="pre">DistributedOptimizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">params_rref</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/optimizer.py#L128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.DistributedOptimizer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.optim.</span></span><span class="sig-name descname"><span class="pre">DistributedOptimizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">params_rref</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/optimizer.py#L128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.DistributedOptimizer" title="Permalink to this definition">#</a></dt>
 <dd><p>DistributedOptimizer takes remote references to parameters scattered
 across workers and applies the given optimizer locally for each parameter.</p>
 <p>This class uses <a class="reference internal" href="rpc.html#torch.distributed.autograd.get_gradients" title="torch.distributed.autograd.get_gradients"><code class="xref py py-meth docutils literal notranslate"><span class="pre">get_gradients()</span></code></a> in order
@@ -4465,7 +4465,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.DistributedOptimizer.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">context_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/optimizer.py#L225"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.DistributedOptimizer.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">context_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/optimizer.py#L225"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.DistributedOptimizer.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs a single optimization step.</p>
 <p>This will call <a class="reference internal" href="generated/torch.optim.Optimizer.step.html#torch.optim.Optimizer.step" title="torch.optim.Optimizer.step"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.optim.Optimizer.step()</span></code></a> on each worker
 containing parameters to be optimized, and will block until all workers
@@ -4484,7 +4484,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.optim.PostLocalSGDOptimizer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.optim.</span></span><span class="sig-name descname"><span class="pre">PostLocalSGDOptimizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">averager</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/post_localSGD_optimizer.py#L8"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.PostLocalSGDOptimizer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.optim.</span></span><span class="sig-name descname"><span class="pre">PostLocalSGDOptimizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">averager</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/post_localSGD_optimizer.py#L8"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.PostLocalSGDOptimizer" title="Permalink to this definition">#</a></dt>
 <dd><p>Wraps an arbitrary <a class="reference internal" href="optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.optim.Optimizer</span></code></a> and runs <a class="reference external" href="https://arxiv.org/abs/1808.07217">post-local SGD</a>,
 This optimizer runs local optimizer at every step.
 After the warm-up stage, it averages parameters periodically after the local optimizer is applied.</p>
@@ -4536,7 +4536,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.PostLocalSGDOptimizer.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/post_localSGD_optimizer.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.PostLocalSGDOptimizer.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/post_localSGD_optimizer.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.PostLocalSGDOptimizer.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the same as <a class="reference internal" href="optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.optim.Optimizer</span></code></a> <a class="reference internal" href="#torch.distributed.optim.PostLocalSGDOptimizer.load_state_dict" title="torch.distributed.optim.PostLocalSGDOptimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a>,
 but also restores model averager’s step value to the one
 saved in the provided <code class="docutils literal notranslate"><span class="pre">state_dict</span></code>.</p>
@@ -4546,7 +4546,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.PostLocalSGDOptimizer.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/post_localSGD_optimizer.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.PostLocalSGDOptimizer.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/post_localSGD_optimizer.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.PostLocalSGDOptimizer.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the same as <a class="reference internal" href="optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.optim.Optimizer</span></code></a> <a class="reference internal" href="#torch.distributed.optim.PostLocalSGDOptimizer.state_dict" title="torch.distributed.optim.PostLocalSGDOptimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a>,
 but adds an extra entry to record model averager’s step to the checkpoint
 to ensure reload does not cause unnecessary warm up again.</p>
@@ -4554,7 +4554,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.PostLocalSGDOptimizer.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/post_localSGD_optimizer.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.PostLocalSGDOptimizer.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/post_localSGD_optimizer.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.PostLocalSGDOptimizer.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs a single optimization step (parameter update).</p>
 </dd></dl>
 
@@ -4562,7 +4562,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.optim.ZeroRedundancyOptimizer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.optim.</span></span><span class="sig-name descname"><span class="pre">ZeroRedundancyOptimizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameters_as_bucket_view</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">overlap_with_ddp</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">defaults</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/zero_redundancy_optimizer.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.optim.</span></span><span class="sig-name descname"><span class="pre">ZeroRedundancyOptimizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameters_as_bucket_view</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">overlap_with_ddp</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">defaults</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/zero_redundancy_optimizer.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrap an arbitrary <a class="reference internal" href="optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">optim.Optimizer</span></code></a> and shards its states across ranks in the group.</p>
 <p>The sharing is done as described by <a class="reference external" href="https://arxiv.org/abs/1910.02054">ZeRO</a>.</p>
 <p>The local optimizer instance in each rank is only
@@ -4652,7 +4652,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.ZeroRedundancyOptimizer.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/zero_redundancy_optimizer.py#L458"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/zero_redundancy_optimizer.py#L458"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a parameter group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> ‘s <code class="docutils literal notranslate"><span class="pre">param_groups</span></code>.</p>
 <p>This can be useful when fine tuning a pre-trained network, as frozen
 layers can be made trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as
@@ -4675,7 +4675,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.ZeroRedundancyOptimizer.consolidate_state_dict">
-<span class="sig-name descname"><span class="pre">consolidate_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/zero_redundancy_optimizer.py#L504"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.consolidate_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">consolidate_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/zero_redundancy_optimizer.py#L504"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.consolidate_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Consolidate a list of <code class="docutils literal notranslate"><span class="pre">state_dict</span></code> s (one per rank) on the target rank.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4703,7 +4703,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.ZeroRedundancyOptimizer.join_hook">
-<span class="sig-name descname"><span class="pre">join_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/zero_redundancy_optimizer.py#L1121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.join_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">join_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/zero_redundancy_optimizer.py#L1121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.join_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the ZeRO join hook.</p>
 <p>It enables training on uneven inputs by
 shadowing the collective communications in the optimizer step.</p>
@@ -4728,7 +4728,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.ZeroRedundancyOptimizer.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/zero_redundancy_optimizer.py#L1151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/zero_redundancy_optimizer.py#L1151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the state pertaining to the given rank from the input <code class="docutils literal notranslate"><span class="pre">state_dict</span></code>, updating the local optimizer as needed.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4747,7 +4747,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.ZeroRedundancyOptimizer.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/zero_redundancy_optimizer.py#L1189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/zero_redundancy_optimizer.py#L1189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the last global optimizer state known to this rank.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Raises</dt>
@@ -4766,7 +4766,7 @@ <h1>Distributed Optimizers<a class="headerlink" href="#distributed-optimizers" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.optim.ZeroRedundancyOptimizer.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/optim/zero_redundancy_optimizer.py#L1090"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/optim/zero_redundancy_optimizer.py#L1090"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.optim.ZeroRedundancyOptimizer.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimizer step and syncs parameters across all ranks.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/distributed.pipelining.html b/2.9/distributed.pipelining.html
index 95cd84655c4..cc4708e3979 100644
--- a/2.9/distributed.pipelining.html
+++ b/2.9/distributed.pipelining.html
@@ -4762,7 +4762,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 <p>The following set of APIs transform your model into a pipeline representation.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.SplitPoint">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.</span></span><span class="sig-name descname"><span class="pre">SplitPoint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/_IR.py#L1142"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.SplitPoint" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.</span></span><span class="sig-name descname"><span class="pre">SplitPoint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/_IR.py#L1142"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.SplitPoint" title="Permalink to this definition">#</a></dt>
 <dd><p>Enum representing the points at which a split can occur in the execution of a submodule.
 :ivar BEGINNING: Represents adding a split point <em>before</em> the execution of a certain submodule in the <cite>forward</cite> function.
 :ivar END: Represents adding a split point <em>after</em> the execution of a certain submodule in the <cite>forward</cite> function.</p>
@@ -4770,7 +4770,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.pipeline">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.</span></span><span class="sig-name descname"><span class="pre">pipeline</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mb_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mb_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/_IR.py#L1197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.pipeline" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.</span></span><span class="sig-name descname"><span class="pre">pipeline</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mb_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mb_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/_IR.py#L1197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.pipeline" title="Permalink to this definition">#</a></dt>
 <dd><p>Split a module based on a specification.</p>
 <p>See <cite>Pipe</cite> for more details.</p>
 <dl class="field-list simple">
@@ -4791,14 +4791,14 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.Pipe">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.</span></span><span class="sig-name descname"><span class="pre">Pipe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">split_gm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_loss_and_backward</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_spec</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/_IR.py#L524"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.Pipe" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.</span></span><span class="sig-name descname"><span class="pre">Pipe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">split_gm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_loss_and_backward</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_spec</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/_IR.py#L524"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.Pipe" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.pipe_split">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.</span></span><span class="sig-name descname"><span class="pre">pipe_split</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/_IR.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.pipe_split" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.</span></span><span class="sig-name descname"><span class="pre">pipe_split</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/_IR.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.pipe_split" title="Permalink to this definition">#</a></dt>
 <dd><p>pipe_split is a special operator that is used to mark the boundary between
 stages in a module. It is used to split the module into stages. It is a
 no-op if your annotated module is run eagerly.</p>
@@ -4819,7 +4819,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 <span id="microbatch-utilities"></span><h3>Microbatch Utilities<a class="headerlink" href="#module-torch.distributed.pipelining.microbatch" title="Permalink to this heading">#</a></h3>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.microbatch.TensorChunkSpec">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.microbatch.</span></span><span class="sig-name descname"><span class="pre">TensorChunkSpec</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">split_dim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/microbatch.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.microbatch.TensorChunkSpec" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.microbatch.</span></span><span class="sig-name descname"><span class="pre">TensorChunkSpec</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">split_dim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/microbatch.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.microbatch.TensorChunkSpec" title="Permalink to this definition">#</a></dt>
 <dd><p>Class used to specify chunking of inputs</p>
 <dl class="field-list simple">
 </dl>
@@ -4827,7 +4827,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.microbatch.split_args_kwargs_into_chunks">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.microbatch.</span></span><span class="sig-name descname"><span class="pre">split_args_kwargs_into_chunks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/microbatch.py#L245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.microbatch.split_args_kwargs_into_chunks" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.microbatch.</span></span><span class="sig-name descname"><span class="pre">split_args_kwargs_into_chunks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/microbatch.py#L245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.microbatch.split_args_kwargs_into_chunks" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a sequence of args and kwargs, split them into a number of chunks
 according to  their respective chunking specs.</p>
 <dl class="field-list simple">
@@ -4852,7 +4852,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.microbatch.merge_chunks">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.microbatch.</span></span><span class="sig-name descname"><span class="pre">merge_chunks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">chunks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_spec</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/microbatch.py#L350"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.microbatch.merge_chunks" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.microbatch.</span></span><span class="sig-name descname"><span class="pre">merge_chunks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">chunks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_spec</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/microbatch.py#L350"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.microbatch.merge_chunks" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a list of chunks, merge them into a single value according to
 the chunk spec.</p>
 <dl class="field-list simple">
@@ -4876,7 +4876,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 <span id="pipeline-stages"></span><h3>Pipeline Stages<a class="headerlink" href="#module-torch.distributed.pipelining.stage" title="Permalink to this heading">#</a></h3>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.stage.PipelineStage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.stage.</span></span><span class="sig-name descname"><span class="pre">PipelineStage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">submodule</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stage_index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dw_builder</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/stage.py#L1299"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.stage.PipelineStage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.stage.</span></span><span class="sig-name descname"><span class="pre">PipelineStage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">submodule</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stage_index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dw_builder</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/stage.py#L1299"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.stage.PipelineStage" title="Permalink to this definition">#</a></dt>
 <dd><p>A class representing a pipeline stage in a pipeline parallelism setup.</p>
 <p>PipelineStage assumes sequential partitioning of the model, i.e. the model is split into chunks where outputs from
 one chunk feed into inputs of the next chunk, with no skip connections.</p>
@@ -4902,7 +4902,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.stage.build_stage">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.stage.</span></span><span class="sig-name descname"><span class="pre">build_stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stage_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stage_index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pipe_info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/stage.py#L1269"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.stage.build_stage" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.stage.</span></span><span class="sig-name descname"><span class="pre">build_stage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stage_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stage_index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pipe_info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/stage.py#L1269"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.stage.build_stage" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a pipeline stage given a stage_module to be wrapped by this stage
 and pipeline information.</p>
 <dl class="field-list simple">
@@ -4929,7 +4929,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 <span id="pipeline-schedules"></span><h3>Pipeline Schedules<a class="headerlink" href="#module-torch.distributed.pipelining.schedules" title="Permalink to this heading">#</a></h3>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.ScheduleGPipe">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleGPipe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L698"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleGPipe" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleGPipe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L698"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleGPipe" title="Permalink to this definition">#</a></dt>
 <dd><p>The GPipe schedule.
 Will go through all the microbatches in a fill-drain manner.</p>
 <dl class="field-list simple">
@@ -4938,7 +4938,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.Schedule1F1B">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">Schedule1F1B</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.Schedule1F1B" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">Schedule1F1B</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.Schedule1F1B" title="Permalink to this definition">#</a></dt>
 <dd><p>The 1F1B schedule.
 Will perform one forward and one backward on the microbatches in steady state.</p>
 <dl class="field-list simple">
@@ -4947,7 +4947,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.ScheduleInterleaved1F1B">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleInterleaved1F1B</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L2304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleInterleaved1F1B" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleInterleaved1F1B</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L2304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleInterleaved1F1B" title="Permalink to this definition">#</a></dt>
 <dd><p>The Interleaved 1F1B schedule.
 See <a class="reference external" href="https://arxiv.org/pdf/2104.04473">https://arxiv.org/pdf/2104.04473</a> for details.
 Will perform one forward and one backward on the microbatches in steady
@@ -4968,7 +4968,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.ScheduleLoopedBFS">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleLoopedBFS</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L2103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleLoopedBFS" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleLoopedBFS</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L2103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleLoopedBFS" title="Permalink to this definition">#</a></dt>
 <dd><p>Breadth-First Pipeline Parallelism.
 See <a class="reference external" href="https://arxiv.org/abs/2211.05953">https://arxiv.org/abs/2211.05953</a> for details.
 Similar to Interleaved 1F1B, Looped BFS supports multiple stages per rank.
@@ -4981,7 +4981,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.ScheduleInterleavedZeroBubble">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleInterleavedZeroBubble</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L2420"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleInterleavedZeroBubble" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleInterleavedZeroBubble</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L2420"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleInterleavedZeroBubble" title="Permalink to this definition">#</a></dt>
 <dd><p>The Interleaved Zero Bubble schedule.
 See <a class="reference external" href="https://arxiv.org/pdf/2401.10241">https://arxiv.org/pdf/2401.10241</a> for details.
 Will perform one forward and one backward on inputs for the microbatches in steady
@@ -4994,7 +4994,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.ScheduleZBVZeroBubble">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleZBVZeroBubble</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L2616"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleZBVZeroBubble" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleZBVZeroBubble</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L2616"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleZBVZeroBubble" title="Permalink to this definition">#</a></dt>
 <dd><p>The Zero Bubble schedule (ZBV variant).
 See <a class="reference external" href="https://arxiv.org/pdf/2401.10241">https://arxiv.org/pdf/2401.10241</a> Section 6 for details.</p>
 <p>This schedules requires exactly two stages per rank.</p>
@@ -5010,7 +5010,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.ScheduleDualPipeV">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleDualPipeV</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L2795"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleDualPipeV" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">ScheduleDualPipeV</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L2795"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.ScheduleDualPipeV" title="Permalink to this definition">#</a></dt>
 <dd><p>The DualPipeV schedule. A more efficient schedule variant based on the
 DualPipe schedule introduced by DeepSeek in <a class="reference external" href="https://arxiv.org/pdf/2412.19437">https://arxiv.org/pdf/2412.19437</a></p>
 <p>Based on the open sourced code from <a class="github reference external" href="https://github.com/deepseek-ai/DualPipe">deepseek-ai/DualPipe</a></p>
@@ -5020,7 +5020,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.PipelineScheduleSingle">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">PipelineScheduleSingle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.PipelineScheduleSingle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">PipelineScheduleSingle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.PipelineScheduleSingle" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class for single-stage schedules.
 Implements the <cite>step</cite> method.
 Derived classes should implement <cite>_step_microbatches</cite>.</p>
@@ -5031,7 +5031,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.PipelineScheduleSingle.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">losses</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L586"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.PipelineScheduleSingle.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">losses</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L586"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.PipelineScheduleSingle.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Run one iteration of the pipeline schedule with <em>whole-batch</em> input.
 Will chunk the input into microbatches automatically, and go through the
 microbatches according to the schedule implementation.</p>
@@ -5047,7 +5047,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.PipelineScheduleMulti">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">PipelineScheduleMulti</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_full_backward</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L1397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.PipelineScheduleMulti" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.pipelining.schedules.</span></span><span class="sig-name descname"><span class="pre">PipelineScheduleMulti</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stages</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_microbatches</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs_chunk_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_merge_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_full_backward</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L1397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.PipelineScheduleMulti" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class for multi-stage schedules.
 Implements the <cite>step</cite> method.</p>
 <p>Gradients are scaled by num_microbatches depending on the <cite>scale_grads</cite> argument, defaulting to True.  This setting
@@ -5057,7 +5057,7 @@ <h3>Model Split APIs<a class="headerlink" href="#model-split-apis" title="Permal
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.pipelining.schedules.PipelineScheduleMulti.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">losses</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/pipelining/schedules.py#L1518"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.PipelineScheduleMulti.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">losses</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/pipelining/schedules.py#L1518"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.pipelining.schedules.PipelineScheduleMulti.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Run one iteration of the pipeline schedule with <em>whole-batch</em> input.
 Will chunk the input into microbatches automatically, and go through the
 microbatches according to the schedule implementation.</p>
diff --git a/2.9/distributed.tensor.html b/2.9/distributed.tensor.html
index e8f376a07f9..8ffe312515a 100644
--- a/2.9/distributed.tensor.html
+++ b/2.9/distributed.tensor.html
@@ -4458,7 +4458,7 @@ <h3>DTensor Class APIs<a class="headerlink" href="#dtensor-class-apis" title="Pe
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.DTensor.__create_chunk_list__">
-<span class="sig-name descname"><span class="pre">__create_chunk_list__</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L621"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.__create_chunk_list__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__create_chunk_list__</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L621"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.__create_chunk_list__" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a list of ChunkStorageMetadata, which is a dataclass that describes the size/offset of the local shard/replica
 on current rank. For DTensor, each rank will have a single local shard/replica, so the returned list usually only
 has one element.</p>
@@ -4472,7 +4472,7 @@ <h3>DTensor Class APIs<a class="headerlink" href="#dtensor-class-apis" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.DTensor.from_local">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_local</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">local_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L355"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.from_local" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_local</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">local_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L355"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.from_local" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a> from a local torch.Tensor on each rank
 according to the <code class="docutils literal notranslate"><span class="pre">device_mesh</span></code> and <code class="docutils literal notranslate"><span class="pre">placements</span></code> specified.</p>
 <dl class="field-list simple">
@@ -4527,7 +4527,7 @@ <h3>DTensor Class APIs<a class="headerlink" href="#dtensor-class-apis" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.DTensor.full_tensor">
-<span class="sig-name descname"><span class="pre">full_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.full_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">full_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.full_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the full tensor of this DTensor. It will perform necessary collectives
 to gather the local tensors from other ranks in its DeviceMesh and concatenate
 them together. It’s a syntactic sugar of the following code:</p>
@@ -4558,7 +4558,7 @@ <h3>DTensor Class APIs<a class="headerlink" href="#dtensor-class-apis" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.DTensor.redistribute">
-<span class="sig-name descname"><span class="pre">redistribute</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forward_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backward_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L477"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.redistribute" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">redistribute</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">async_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forward_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backward_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L477"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.redistribute" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">redistribute</span></code> performs necessary collective operations that redistribute the current
 DTensor from its current placements to a new placements, or from its current DeviceMesh
 to a new DeviceMesh. i.e. we can turn a Sharded DTensor to a Replicated DTensor by
@@ -4619,7 +4619,7 @@ <h3>DTensor Class APIs<a class="headerlink" href="#dtensor-class-apis" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.DTensor.to_local">
-<span class="sig-name descname"><span class="pre">to_local</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L440"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.to_local" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_local</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L440"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.DTensor.to_local" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the local tensor of this DTensor on its current rank. For sharding it returns
 a local shard of the logical tensor view, for replication it returns the replica on
 its current rank.</p>
@@ -4687,7 +4687,7 @@ <h3>DeviceMesh as the distributed communicator<a class="headerlink" href="#devic
 <p>DTensor supports the following types of <a class="reference internal" href="#torch.distributed.tensor.placement_types.Placement" title="torch.distributed.tensor.placement_types.Placement"><code class="xref py py-class docutils literal notranslate"><span class="pre">Placement</span></code></a> on each <code class="xref py py-class docutils literal notranslate"><span class="pre">DeviceMesh</span></code> dimension:</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.placement_types.Shard">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.placement_types.</span></span><span class="sig-name descname"><span class="pre">Shard</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/placement_types.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Shard" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.placement_types.</span></span><span class="sig-name descname"><span class="pre">Shard</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/placement_types.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Shard" title="Permalink to this definition">#</a></dt>
 <dd><p>The <code class="docutils literal notranslate"><span class="pre">Shard(dim)</span></code> placement describes the DTensor sharding on tensor dimension
 <code class="docutils literal notranslate"><span class="pre">dim</span></code> over a corresponding <code class="docutils literal notranslate"><span class="pre">DeviceMesh</span></code> dimension, where each rank on the
 DeviceMesh dimension only holds a shard/piece of the global Tensor. The
@@ -4715,7 +4715,7 @@ <h3>DeviceMesh as the distributed communicator<a class="headerlink" href="#devic
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.placement_types.Replicate">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.placement_types.</span></span><span class="sig-name descname"><span class="pre">Replicate</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/placement_types.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Replicate" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.placement_types.</span></span><span class="sig-name descname"><span class="pre">Replicate</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/placement_types.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Replicate" title="Permalink to this definition">#</a></dt>
 <dd><p>The <code class="docutils literal notranslate"><span class="pre">Replicate()</span></code> placement describes the DTensor replicating on a corresponding
 <code class="docutils literal notranslate"><span class="pre">DeviceMesh</span></code> dimension, where each rank on the DeviceMesh dimension holds a
 replica of the global Tensor. The <code class="docutils literal notranslate"><span class="pre">Replicate</span></code> placement can be used by all
@@ -4726,7 +4726,7 @@ <h3>DeviceMesh as the distributed communicator<a class="headerlink" href="#devic
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.placement_types.Partial">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.placement_types.</span></span><span class="sig-name descname"><span class="pre">Partial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reduce_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'sum'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/placement_types.py#L654"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Partial" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.placement_types.</span></span><span class="sig-name descname"><span class="pre">Partial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reduce_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'sum'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/placement_types.py#L654"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Partial" title="Permalink to this definition">#</a></dt>
 <dd><p>The <code class="docutils literal notranslate"><span class="pre">Partial(reduce_op)</span></code> placement describes the DTensor that is pending
 reduction on a specified <code class="docutils literal notranslate"><span class="pre">DeviceMesh</span></code> dimension, where each rank on the
 DeviceMesh dimension holds the partial value of the global Tensor. User can
@@ -4755,7 +4755,7 @@ <h3>DeviceMesh as the distributed communicator<a class="headerlink" href="#devic
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.placement_types.Placement">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.placement_types.</span></span><span class="sig-name descname"><span class="pre">Placement</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/placement_types.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Placement" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.placement_types.</span></span><span class="sig-name descname"><span class="pre">Placement</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/placement_types.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Placement" title="Permalink to this definition">#</a></dt>
 <dd><p>The base class for the Placement type, where it describes how a DTensor is placed onto the
 <code class="docutils literal notranslate"><span class="pre">DeviceMesh</span></code>. <code class="docutils literal notranslate"><span class="pre">Placement</span></code> and <code class="docutils literal notranslate"><span class="pre">DeviceMesh</span></code> together could describe the DTensor Layout.
 It is the base class of the three main DTensor Placement types: <code class="docutils literal notranslate"><span class="pre">Shard</span></code>, <code class="docutils literal notranslate"><span class="pre">Replicate</span></code>,
@@ -4763,7 +4763,7 @@ <h3>DeviceMesh as the distributed communicator<a class="headerlink" href="#devic
 <p>This class is not meant to be used directly, mainly served as a typing stub.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.placement_types.Placement.is_partial">
-<span class="sig-name descname"><span class="pre">is_partial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reduce_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/placement_types.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Placement.is_partial" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_partial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reduce_op</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/placement_types.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Placement.is_partial" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)">bool</a></p>
@@ -4773,7 +4773,7 @@ <h3>DeviceMesh as the distributed communicator<a class="headerlink" href="#devic
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.placement_types.Placement.is_replicate">
-<span class="sig-name descname"><span class="pre">is_replicate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/placement_types.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Placement.is_replicate" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_replicate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/placement_types.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Placement.is_replicate" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)">bool</a></p>
@@ -4783,7 +4783,7 @@ <h3>DeviceMesh as the distributed communicator<a class="headerlink" href="#devic
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.placement_types.Placement.is_shard">
-<span class="sig-name descname"><span class="pre">is_shard</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/placement_types.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Placement.is_shard" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_shard</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/placement_types.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.placement_types.Placement.is_shard" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)">bool</a></p>
@@ -4823,7 +4823,7 @@ <h3>Create DTensor from a logical torch.Tensor<a class="headerlink" href="#creat
 <code class="docutils literal notranslate"><span class="pre">DTensor</span></code> s to comply with the single device semantic, which is critical for <strong>numerical correctness</strong>.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.distribute_tensor">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">distribute_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_data_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L652"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.distribute_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">distribute_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_data_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L652"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.distribute_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Distribute a leaf <code class="docutils literal notranslate"><span class="pre">torch.Tensor</span></code> (i.e. nn.Parameter/buffers) to the <code class="docutils literal notranslate"><span class="pre">device_mesh</span></code> according
 to the <code class="docutils literal notranslate"><span class="pre">placements</span></code> specified. The rank of <code class="docutils literal notranslate"><span class="pre">device_mesh</span></code> and <code class="docutils literal notranslate"><span class="pre">placements</span></code> must be the
 same. The <code class="docutils literal notranslate"><span class="pre">tensor</span></code> to distribute is the logical or “global” tensor, and the API would use
@@ -4875,7 +4875,7 @@ <h3>Create DTensor from a logical torch.Tensor<a class="headerlink" href="#creat
 sharding on the <code class="xref py py-class docutils literal notranslate"><span class="pre">nn.Module</span></code> level</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.distribute_module">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">distribute_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">partition_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L836"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.distribute_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">distribute_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">partition_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L836"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.distribute_module" title="Permalink to this definition">#</a></dt>
 <dd><p>This function expose three functions to control the parameters/inputs/outputs of the module:</p>
 <p>1. To perform sharding on the module before runtime execution by specifying the
 <code class="docutils literal notranslate"><span class="pre">partition_fn</span></code> (i.e. allow user to convert Module parameters to <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a>
@@ -4923,7 +4923,7 @@ <h3>DTensor Factory Functions<a class="headerlink" href="#dtensor-factory-functi
 specifying the <code class="xref py py-class docutils literal notranslate"><span class="pre">DeviceMesh</span></code> and <code class="xref py py-class docutils literal notranslate"><span class="pre">Placement</span></code> for the <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a> created:</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.zeros">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">zeros</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L1276"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.zeros" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">zeros</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L1276"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.zeros" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a> filled with the scalar value 0.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4954,7 +4954,7 @@ <h3>DTensor Factory Functions<a class="headerlink" href="#dtensor-factory-functi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.ones">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">ones</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L1055"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.ones" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">ones</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L1055"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.ones" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a> filled with the scalar value 1, with the shape defined
 by the variable argument <code class="docutils literal notranslate"><span class="pre">size</span></code>.</p>
 <dl class="field-list simple">
@@ -4986,7 +4986,7 @@ <h3>DTensor Factory Functions<a class="headerlink" href="#dtensor-factory-functi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.empty">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">empty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L1098"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.empty" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">empty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L1098"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.empty" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a> filled with uninitialized data. The shape of the <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a>
 is defined by the variable argument <code class="docutils literal notranslate"><span class="pre">size</span></code>.</p>
 <dl class="field-list simple">
@@ -5017,7 +5017,7 @@ <h3>DTensor Factory Functions<a class="headerlink" href="#dtensor-factory-functi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.full">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">full</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fill_value</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L1141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.full" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">full</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fill_value</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L1141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.full" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a> filled with <code class="docutils literal notranslate"><span class="pre">fill_value</span></code> according to <code class="docutils literal notranslate"><span class="pre">device_mesh</span></code> and
 <code class="docutils literal notranslate"><span class="pre">placements</span></code>, with the shape defined by the argument <code class="docutils literal notranslate"><span class="pre">size</span></code>.</p>
 <dl class="field-list simple">
@@ -5052,7 +5052,7 @@ <h3>DTensor Factory Functions<a class="headerlink" href="#dtensor-factory-functi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.rand">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">rand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L1188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.rand" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">rand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L1188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.rand" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a> filled with random numbers from a uniform distribution
 on the interval <code class="docutils literal notranslate"><span class="pre">[0,</span> <span class="pre">1)</span></code>. The shape of the tensor is defined by the variable
 argument <code class="docutils literal notranslate"><span class="pre">size</span></code>.</p>
@@ -5085,7 +5085,7 @@ <h3>DTensor Factory Functions<a class="headerlink" href="#dtensor-factory-functi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.randn">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">randn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/_api.py#L1232"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.randn" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.</span></span><span class="sig-name descname"><span class="pre">randn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/_api.py#L1232"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.randn" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a <a class="reference internal" href="#torch.distributed.tensor.DTensor" title="torch.distributed.tensor.DTensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code></a> filled with random numbers from a normal distribution
 with mean 0 and variance 1. The shape of the tensor is defined by the variable
 argument <code class="docutils literal notranslate"><span class="pre">size</span></code>.</p>
@@ -5163,7 +5163,7 @@ <h3>Debugging Tools<a class="headerlink" href="#debugging-tools" title="Permalin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.debug.CommDebugMode.generate_comm_debug_tracing_table">
-<span class="sig-name descname"><span class="pre">generate_comm_debug_tracing_table</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">noise_level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/debug/_comm_mode.py#L402"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.generate_comm_debug_tracing_table" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">generate_comm_debug_tracing_table</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">noise_level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/debug/_comm_mode.py#L402"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.generate_comm_debug_tracing_table" title="Permalink to this definition">#</a></dt>
 <dd><p>Generates detailed table displaying operations and collective tracing information
 on a module level. Amount of information is dependent on noise_level</p>
 <ol class="arabic simple" start="0">
@@ -5176,7 +5176,7 @@ <h3>Debugging Tools<a class="headerlink" href="#debugging-tools" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.debug.CommDebugMode.generate_json_dump">
-<span class="sig-name descname"><span class="pre">generate_json_dump</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'comm_mode_log.json'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">noise_level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/debug/_comm_mode.py#L254"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.generate_json_dump" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">generate_json_dump</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'comm_mode_log.json'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">noise_level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/debug/_comm_mode.py#L254"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.generate_json_dump" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates json file used to build browser visual
 0. prints module-level collective counts
 1. prints dTensor operations not included in trivial operations
@@ -5186,7 +5186,7 @@ <h3>Debugging Tools<a class="headerlink" href="#debugging-tools" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.debug.CommDebugMode.get_comm_counts">
-<span class="sig-name descname"><span class="pre">get_comm_counts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/debug/_comm_mode.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.get_comm_counts" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_comm_counts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/debug/_comm_mode.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.get_comm_counts" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the communication counts as a dictionary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5200,7 +5200,7 @@ <h3>Debugging Tools<a class="headerlink" href="#debugging-tools" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.debug.CommDebugMode.get_parameter_info">
-<span class="sig-name descname"><span class="pre">get_parameter_info</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/debug/_comm_mode.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.get_parameter_info" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_parameter_info</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/debug/_comm_mode.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.get_parameter_info" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)">dict</a>[<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)">str</a>, <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)">dict</a>[<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)">str</a>, <a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Any" title="(in Python v3.14)"><em>Any</em></a>]]</p>
@@ -5210,7 +5210,7 @@ <h3>Debugging Tools<a class="headerlink" href="#debugging-tools" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.debug.CommDebugMode.get_sharding_info">
-<span class="sig-name descname"><span class="pre">get_sharding_info</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/debug/_comm_mode.py#L581"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.get_sharding_info" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_sharding_info</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/debug/_comm_mode.py#L581"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.get_sharding_info" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)">dict</a>[<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)">str</a>, <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)">dict</a>[<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)">str</a>, <a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Any" title="(in Python v3.14)"><em>Any</em></a>]]</p>
@@ -5220,7 +5220,7 @@ <h3>Debugging Tools<a class="headerlink" href="#debugging-tools" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.debug.CommDebugMode.get_total_counts">
-<span class="sig-name descname"><span class="pre">get_total_counts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/debug/_comm_mode.py#L567"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.get_total_counts" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_total_counts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/debug/_comm_mode.py#L567"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.get_total_counts" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)">int</a></p>
@@ -5230,7 +5230,7 @@ <h3>Debugging Tools<a class="headerlink" href="#debugging-tools" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.tensor.debug.CommDebugMode.log_comm_debug_tracing_table_to_file">
-<span class="sig-name descname"><span class="pre">log_comm_debug_tracing_table_to_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'comm_mode_log.txt'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">noise_level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/debug/_comm_mode.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.log_comm_debug_tracing_table_to_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_comm_debug_tracing_table_to_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'comm_mode_log.txt'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">noise_level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/debug/_comm_mode.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.CommDebugMode.log_comm_debug_tracing_table_to_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Alternative to console CommDebugMode output, writes to file specified by the user</p>
 </dd></dl>
 
@@ -5239,7 +5239,7 @@ <h3>Debugging Tools<a class="headerlink" href="#debugging-tools" title="Permalin
 <p>To visualize the sharding of a DTensor that have less than 3 dimensions, DTensor provides <a class="reference internal" href="#torch.distributed.tensor.debug.visualize_sharding" title="torch.distributed.tensor.debug.visualize_sharding"><code class="xref py py-meth docutils literal notranslate"><span class="pre">visualize_sharding()</span></code></a>:</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.debug.visualize_sharding">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.debug.</span></span><span class="sig-name descname"><span class="pre">visualize_sharding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">header</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_rich</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/debug/_visualize_sharding.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.visualize_sharding" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.debug.</span></span><span class="sig-name descname"><span class="pre">visualize_sharding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">header</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_rich</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/debug/_visualize_sharding.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.debug.visualize_sharding" title="Permalink to this definition">#</a></dt>
 <dd><p>Visualizes sharding in the terminal for <code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code> that are 1D or 2D.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -5259,7 +5259,7 @@ <h2>Experimental Features<a class="headerlink" href="#experimental-features" tit
 these features.</p>
 <span class="target" id="module-torch.distributed.tensor.experimental"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.experimental.context_parallel">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.experimental.</span></span><span class="sig-name descname"><span class="pre">context_parallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mesh</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffer_seq_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_restore_buffers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/experimental/_attention.py#L1399"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.experimental.context_parallel" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.experimental.</span></span><span class="sig-name descname"><span class="pre">context_parallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mesh</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffer_seq_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">no_restore_buffers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/experimental/_attention.py#L1399"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.experimental.context_parallel" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">context_parallel</span></code> is an experimental API to enable context
 parallelism (CP). This API performs two actions: 1) patch the SDPA
 (<code class="docutils literal notranslate"><span class="pre">torch.nn.functional.scaled_dot_product_attention</span></code>) with the CP-enabled
@@ -5298,7 +5298,7 @@ <h2>Experimental Features<a class="headerlink" href="#experimental-features" tit
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.experimental.local_map">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.experimental.</span></span><span class="sig-name descname"><span class="pre">local_map</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_grad_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">redistribute_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/experimental/_func_map.py#L26"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.experimental.local_map" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.experimental.</span></span><span class="sig-name descname"><span class="pre">local_map</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_grad_placements</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">redistribute_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/experimental/_func_map.py#L26"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.experimental.local_map" title="Permalink to this definition">#</a></dt>
 <dd><p><a class="reference internal" href="#torch.distributed.tensor.experimental.local_map" title="torch.distributed.tensor.experimental.local_map"><code class="xref py py-meth docutils literal notranslate"><span class="pre">local_map()</span></code></a> is an experimental API that allows users to pass <code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code> s
 to a function that is written to be applied on <code class="docutils literal notranslate"><span class="pre">torch.Tensor</span></code> s. It is done by extracting
 the local components of <code class="xref py py-class docutils literal notranslate"><span class="pre">DTensor</span></code>, call the function, and wrap the outputs to
@@ -5403,7 +5403,7 @@ <h2>Experimental Features<a class="headerlink" href="#experimental-features" tit
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.experimental.register_sharding">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.experimental.</span></span><span class="sig-name descname"><span class="pre">register_sharding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/experimental/_register_sharding.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.experimental.register_sharding" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.experimental.</span></span><span class="sig-name descname"><span class="pre">register_sharding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/experimental/_register_sharding.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.experimental.register_sharding" title="Permalink to this definition">#</a></dt>
 <dd><p><a class="reference internal" href="#torch.distributed.tensor.experimental.register_sharding" title="torch.distributed.tensor.experimental.register_sharding"><code class="xref py py-meth docutils literal notranslate"><span class="pre">register_sharding()</span></code></a> is an experimental API that allows users to register sharding
 strategies for an operator when the tensor inputs and outputs are DTensor.
 It can be useful when: (1) there doesn’t exist a default sharding strategy for <code class="docutils literal notranslate"><span class="pre">op</span></code>,
diff --git a/2.9/distributed.tensor.parallel.html b/2.9/distributed.tensor.parallel.html
index 13cafd69648..f4fa92db8d7 100644
--- a/2.9/distributed.tensor.parallel.html
+++ b/2.9/distributed.tensor.parallel.html
@@ -4404,7 +4404,7 @@ <h1>Tensor Parallelism - torch.distributed.tensor.parallel<a class="headerlink"
 <p>The entrypoint to parallelize your <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> using Tensor Parallelism is:</p>
 <span class="target" id="module-torch.distributed.tensor.parallel"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.parallel.parallelize_module">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">parallelize_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parallelize_plan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_data_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/parallel/api.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.parallelize_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">parallelize_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parallelize_plan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_data_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/parallel/api.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.parallelize_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply Tensor Parallelism in PyTorch by parallelizing modules or sub-modules based on a user-specified plan.</p>
 <p>We parallelize module or sub_modules based on a parallelize_plan. The parallelize_plan contains
 <code class="xref py py-class docutils literal notranslate"><span class="pre">ParallelStyle</span></code>, which indicates how user wants the module or sub_module
@@ -4463,7 +4463,7 @@ <h1>Tensor Parallelism - torch.distributed.tensor.parallel<a class="headerlink"
 <p>Tensor Parallelism supports the following parallel styles:</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.parallel.ColwiseParallel">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">ColwiseParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/parallel/style.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.ColwiseParallel" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">ColwiseParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/parallel/style.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.ColwiseParallel" title="Permalink to this definition">#</a></dt>
 <dd><p>Partition a compatible nn.Module in a column-wise fashion. Currently supports nn.Linear and nn.Embedding.
 Users can compose it together with RowwiseParallel to achieve the sharding of more complicated modules.
 (i.e. MLP, Attention)</p>
@@ -4507,7 +4507,7 @@ <h1>Tensor Parallelism - torch.distributed.tensor.parallel<a class="headerlink"
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.parallel.RowwiseParallel">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">RowwiseParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/parallel/style.py#L179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.RowwiseParallel" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">RowwiseParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/parallel/style.py#L179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.RowwiseParallel" title="Permalink to this definition">#</a></dt>
 <dd><p>Partition a compatible nn.Module in a row-wise fashion. Currently supports nn.Linear and nn.Embedding.
 Users can compose it with ColwiseParallel to achieve the sharding of more complicated modules.
 (i.e. MLP, Attention)</p>
@@ -4545,7 +4545,7 @@ <h1>Tensor Parallelism - torch.distributed.tensor.parallel<a class="headerlink"
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.parallel.SequenceParallel">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">SequenceParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sequence_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/parallel/style.py#L324"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.SequenceParallel" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">SequenceParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sequence_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/parallel/style.py#L324"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.SequenceParallel" title="Permalink to this definition">#</a></dt>
 <dd><p>SequenceParallel replicates a compatible <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> parameters and runs the sharded computation with
 input sharded on the sequence dimension. This currently supports <code class="docutils literal notranslate"><span class="pre">nn.LayerNorm</span></code>, <code class="docutils literal notranslate"><span class="pre">nn.Dropout</span></code>, and the
 <a class="reference external" href="https://github.com/facebookresearch/llama/blob/main/llama/model.py#L34">RMSNorm python implementation</a></p>
@@ -4599,7 +4599,7 @@ <h1>Tensor Parallelism - torch.distributed.tensor.parallel<a class="headerlink"
 the <code class="docutils literal notranslate"><span class="pre">parallelize_plan</span></code> when calling <code class="docutils literal notranslate"><span class="pre">parallelize_module</span></code>:</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.parallel.PrepareModuleInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">PrepareModuleInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_kwarg_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_input_kwarg_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/parallel/style.py#L427"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.PrepareModuleInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">PrepareModuleInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_kwarg_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_input_kwarg_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/parallel/style.py#L427"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.PrepareModuleInput" title="Permalink to this definition">#</a></dt>
 <dd><p>Configure the nn.Module’s inputs to convert the input tensors of the nn.Module to DTensors at runtime according to
 <code class="docutils literal notranslate"><span class="pre">input_layouts</span></code>, and perform layout redistribution according to the <code class="docutils literal notranslate"><span class="pre">desired_input_layouts</span></code>.</p>
 <dl class="field-list simple">
@@ -4649,7 +4649,7 @@ <h1>Tensor Parallelism - torch.distributed.tensor.parallel<a class="headerlink"
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.parallel.PrepareModuleOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">PrepareModuleOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_layouts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_output_layouts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/parallel/style.py#L596"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.PrepareModuleOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">PrepareModuleOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_layouts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_output_layouts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/parallel/style.py#L596"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.PrepareModuleOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>Configure the nn.Module’s outputs to convert the output tensors of the nn.Module to DTensors at runtime according to
 <code class="docutils literal notranslate"><span class="pre">output_layouts</span></code>, and perform layout redistribution according to the <code class="docutils literal notranslate"><span class="pre">desired_output_layouts</span></code>.</p>
 <dl class="field-list simple">
@@ -4692,7 +4692,7 @@ <h1>Tensor Parallelism - torch.distributed.tensor.parallel<a class="headerlink"
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.tensor.parallel.PrepareModuleInputOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">PrepareModuleInputOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_kwarg_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_input_kwarg_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_layouts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_output_layouts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/parallel/style.py#L704"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.PrepareModuleInputOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">PrepareModuleInputOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_input_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_kwarg_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_input_kwarg_layouts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_layouts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">desired_output_layouts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_local_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/parallel/style.py#L704"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.PrepareModuleInputOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>Configure the nn.Module’s inputs (and outputs) to convert the input tensors (and output tensors, respectively) of the nn.Module
 to DTensors at runtime according to <code class="docutils literal notranslate"><span class="pre">input_layouts</span></code> (and output_layouts, respectively), and perform layout redistribution
 according to the <code class="docutils literal notranslate"><span class="pre">desired_input_layouts</span></code> (and <code class="docutils literal notranslate"><span class="pre">desired_output_layouts</span></code>, respectively). This is a combination of
@@ -4765,7 +4765,7 @@ <h1>Tensor Parallelism - torch.distributed.tensor.parallel<a class="headerlink"
 <p>Parallelized cross-entropy loss computation (loss parallelism), is supported via the following context manager:</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.tensor.parallel.loss_parallel">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">loss_parallel</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/tensor/parallel/loss.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.loss_parallel" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.tensor.parallel.</span></span><span class="sig-name descname"><span class="pre">loss_parallel</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/tensor/parallel/loss.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.tensor.parallel.loss_parallel" title="Permalink to this definition">#</a></dt>
 <dd><p>A context manager that enables loss parallelism, where efficient parallelized loss computation
 can be performed when the input is sharded on the class dimension. Currently only the cross-entropy
 loss is supported.</p>
diff --git a/2.9/distributions.html b/2.9/distributions.html
index 762c096201c..4c2beb1b710 100644
--- a/2.9/distributions.html
+++ b/2.9/distributions.html
@@ -4456,7 +4456,7 @@ <h2>Pathwise derivative<a class="headerlink" href="#pathwise-derivative" title="
 <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="#distribution" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.distribution.</span></span><span class="sig-name descname"><span class="pre">Distribution</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.distribution.</span></span><span class="sig-name descname"><span class="pre">Distribution</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></a></p>
 <p>Distribution is the abstract base class for probability distributions.</p>
 <dl class="field-list simple">
@@ -4485,7 +4485,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.cdf" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the cumulative density/mass function evaluated at
 <cite>value</cite>.</p>
 <dl class="field-list simple">
@@ -4500,7 +4500,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L248"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L248"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.entropy" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns entropy of distribution, batched over batch_shape.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4514,7 +4514,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.enumerate_support">
-<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.enumerate_support" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.enumerate_support" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns tensor containing all values supported by a discrete
 distribution. The result will enumerate over dimension 0, so the shape
 of the result will be <cite>(cardinality,) + batch_shape + event_shape</cite>
@@ -4547,7 +4547,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.expand" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a new distribution instance (or populates an existing instance
 provided by a derived class) with batch dimensions expanded to
 <cite>batch_shape</cite>. This method calls <a class="reference internal" href="generated/torch.Tensor.expand.html#torch.Tensor.expand" title="torch.Tensor.expand"><code class="xref py py-class docutils literal notranslate"><span class="pre">expand</span></code></a> on
@@ -4572,7 +4572,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.icdf" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the inverse cumulative density/mass function evaluated at
 <cite>value</cite>.</p>
 <dl class="field-list simple">
@@ -4587,7 +4587,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.log_prob" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the log of the probability density/mass function evaluated at
 <cite>value</cite>.</p>
 <dl class="field-list simple">
@@ -4614,7 +4614,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.perplexity">
-<span class="sig-name descname"><span class="pre">perplexity</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.perplexity" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">perplexity</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.perplexity" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns perplexity of distribution, batched over batch_shape.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4628,7 +4628,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.rsample" title="Permalink to this definition">#</a></dt>
 <dd><p>Generates a sample_shape shaped reparameterized sample or sample_shape
 shaped batch of reparameterized samples if the distribution parameters
 are batched.</p>
@@ -4641,7 +4641,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.sample" title="Permalink to this definition">#</a></dt>
 <dd><p>Generates a sample_shape shaped sample or sample_shape shaped batch of
 samples if the distribution parameters are batched.</p>
 <dl class="field-list simple">
@@ -4653,7 +4653,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.sample_n">
-<span class="sig-name descname"><span class="pre">sample_n</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.sample_n" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample_n</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.sample_n" title="Permalink to this definition">#</a></dt>
 <dd><p>Generates n samples or n batches of samples if the distribution
 parameters are batched.</p>
 <dl class="field-list simple">
@@ -4665,7 +4665,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.distribution.Distribution.set_default_validate_args">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_default_validate_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/distribution.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.set_default_validate_args" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_default_validate_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/distribution.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.distribution.Distribution.set_default_validate_args" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether validation is enabled or disabled.</p>
 <p>The default behavior mimics Python’s <code class="docutils literal notranslate"><span class="pre">assert</span></code> statement: validation
 is on by default, but is disabled if Python is run in optimized mode
@@ -4704,7 +4704,7 @@ <h2><span class="hidden-section">Distribution</span><a class="headerlink" href="
 <h2><span class="hidden-section">ExponentialFamily</span><a class="headerlink" href="#exponentialfamily" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.exp_family.ExponentialFamily">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.exp_family.</span></span><span class="sig-name descname"><span class="pre">ExponentialFamily</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exp_family.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exp_family.ExponentialFamily" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.exp_family.</span></span><span class="sig-name descname"><span class="pre">ExponentialFamily</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exp_family.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exp_family.ExponentialFamily" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>ExponentialFamily is the abstract base class for probability distributions belonging to an
 exponential family, whose probability mass/density function has the form is defined below</p>
@@ -4724,7 +4724,7 @@ <h2><span class="hidden-section">ExponentialFamily</span><a class="headerlink" h
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.exp_family.ExponentialFamily.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exp_family.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exp_family.ExponentialFamily.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exp_family.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exp_family.ExponentialFamily.entropy" title="Permalink to this definition">#</a></dt>
 <dd><p>Method to compute the entropy using Bregman divergence of the log normalizer.</p>
 </dd></dl>
 
@@ -4735,7 +4735,7 @@ <h2><span class="hidden-section">ExponentialFamily</span><a class="headerlink" h
 <h2><span class="hidden-section">Bernoulli</span><a class="headerlink" href="#bernoulli" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.bernoulli.Bernoulli">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.bernoulli.</span></span><span class="sig-name descname"><span class="pre">Bernoulli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/bernoulli.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.bernoulli.</span></span><span class="sig-name descname"><span class="pre">Bernoulli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/bernoulli.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Creates a Bernoulli distribution parameterized by <a class="reference internal" href="#torch.distributions.bernoulli.Bernoulli.probs" title="torch.distributions.bernoulli.Bernoulli.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a>
 or <a class="reference internal" href="#torch.distributions.bernoulli.Bernoulli.logits" title="torch.distributions.bernoulli.Bernoulli.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a> (but not both).</p>
@@ -4763,17 +4763,17 @@ <h2><span class="hidden-section">Bernoulli</span><a class="headerlink" href="#be
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.bernoulli.Bernoulli.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/bernoulli.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/bernoulli.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.bernoulli.Bernoulli.enumerate_support">
-<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/bernoulli.py#L129"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.enumerate_support" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/bernoulli.py#L129"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.enumerate_support" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.bernoulli.Bernoulli.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/bernoulli.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/bernoulli.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -4783,7 +4783,7 @@ <h2><span class="hidden-section">Bernoulli</span><a class="headerlink" href="#be
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.bernoulli.Bernoulli.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/bernoulli.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/bernoulli.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -4813,7 +4813,7 @@ <h2><span class="hidden-section">Bernoulli</span><a class="headerlink" href="#be
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.bernoulli.Bernoulli.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/bernoulli.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/bernoulli.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.bernoulli.Bernoulli.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -4833,7 +4833,7 @@ <h2><span class="hidden-section">Bernoulli</span><a class="headerlink" href="#be
 <h2><span class="hidden-section">Beta</span><a class="headerlink" href="#beta" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.beta.Beta">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.beta.</span></span><span class="sig-name descname"><span class="pre">Beta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/beta.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.beta.</span></span><span class="sig-name descname"><span class="pre">Beta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/beta.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Beta distribution parameterized by <a class="reference internal" href="#torch.distributions.beta.Beta.concentration1" title="torch.distributions.beta.Beta.concentration1"><code class="xref py py-attr docutils literal notranslate"><span class="pre">concentration1</span></code></a> and <a class="reference internal" href="#torch.distributions.beta.Beta.concentration0" title="torch.distributions.beta.Beta.concentration0"><code class="xref py py-attr docutils literal notranslate"><span class="pre">concentration0</span></code></a>.</p>
 <p>Example:</p>
@@ -4869,12 +4869,12 @@ <h2><span class="hidden-section">Beta</span><a class="headerlink" href="#beta" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.beta.Beta.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/beta.py#L93"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/beta.py#L93"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.beta.Beta.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/beta.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/beta.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -4884,7 +4884,7 @@ <h2><span class="hidden-section">Beta</span><a class="headerlink" href="#beta" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.beta.Beta.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/beta.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/beta.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -4899,7 +4899,7 @@ <h2><span class="hidden-section">Beta</span><a class="headerlink" href="#beta" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.beta.Beta.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/beta.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/beta.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.beta.Beta.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -4924,7 +4924,7 @@ <h2><span class="hidden-section">Beta</span><a class="headerlink" href="#beta" t
 <h2><span class="hidden-section">Binomial</span><a class="headerlink" href="#binomial" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.binomial.Binomial">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.binomial.</span></span><span class="sig-name descname"><span class="pre">Binomial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">total_count</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/binomial.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.binomial.</span></span><span class="sig-name descname"><span class="pre">Binomial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">total_count</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/binomial.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a Binomial distribution parameterized by <code class="xref py py-attr docutils literal notranslate"><span class="pre">total_count</span></code> and
 either <a class="reference internal" href="#torch.distributions.binomial.Binomial.probs" title="torch.distributions.binomial.Binomial.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a> or <a class="reference internal" href="#torch.distributions.binomial.Binomial.logits" title="torch.distributions.binomial.Binomial.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a> (but not both). <code class="xref py py-attr docutils literal notranslate"><span class="pre">total_count</span></code> must be
@@ -4956,17 +4956,17 @@ <h2><span class="hidden-section">Binomial</span><a class="headerlink" href="#bin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.binomial.Binomial.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/binomial.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/binomial.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.binomial.Binomial.enumerate_support">
-<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/binomial.py#L166"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.enumerate_support" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/binomial.py#L166"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.enumerate_support" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.binomial.Binomial.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/binomial.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/binomial.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -4976,7 +4976,7 @@ <h2><span class="hidden-section">Binomial</span><a class="headerlink" href="#bin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.binomial.Binomial.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/binomial.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/binomial.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5006,7 +5006,7 @@ <h2><span class="hidden-section">Binomial</span><a class="headerlink" href="#bin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.binomial.Binomial.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/binomial.py#L129"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/binomial.py#L129"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.binomial.Binomial.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5031,7 +5031,7 @@ <h2><span class="hidden-section">Binomial</span><a class="headerlink" href="#bin
 <h2><span class="hidden-section">Categorical</span><a class="headerlink" href="#categorical" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.categorical.Categorical">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.categorical.</span></span><span class="sig-name descname"><span class="pre">Categorical</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/categorical.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.categorical.</span></span><span class="sig-name descname"><span class="pre">Categorical</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/categorical.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a categorical distribution parameterized by either <a class="reference internal" href="#torch.distributions.categorical.Categorical.probs" title="torch.distributions.categorical.Categorical.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a> or
 <a class="reference internal" href="#torch.distributions.categorical.Categorical.logits" title="torch.distributions.categorical.Categorical.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a> (but not both).</p>
@@ -5077,17 +5077,17 @@ <h2><span class="hidden-section">Categorical</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.categorical.Categorical.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/categorical.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/categorical.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.categorical.Categorical.enumerate_support">
-<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/categorical.py#L160"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.enumerate_support" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/categorical.py#L160"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.enumerate_support" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.categorical.Categorical.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/categorical.py#L83"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/categorical.py#L83"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5097,7 +5097,7 @@ <h2><span class="hidden-section">Categorical</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.categorical.Categorical.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/categorical.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/categorical.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5127,7 +5127,7 @@ <h2><span class="hidden-section">Categorical</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.categorical.Categorical.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/categorical.py#L139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/categorical.py#L139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.categorical.Categorical.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5152,7 +5152,7 @@ <h2><span class="hidden-section">Categorical</span><a class="headerlink" href="#
 <h2><span class="hidden-section">Cauchy</span><a class="headerlink" href="#cauchy" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.cauchy.Cauchy">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.cauchy.</span></span><span class="sig-name descname"><span class="pre">Cauchy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/cauchy.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.cauchy.</span></span><span class="sig-name descname"><span class="pre">Cauchy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/cauchy.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Samples from a Cauchy (Lorentz) distribution. The distribution of the ratio of
 independent normally distributed random variables with means <cite>0</cite> follows a
@@ -5178,17 +5178,17 @@ <h2><span class="hidden-section">Cauchy</span><a class="headerlink" href="#cauch
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.cauchy.Cauchy.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/cauchy.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/cauchy.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.cauchy.Cauchy.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/cauchy.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/cauchy.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.cauchy.Cauchy.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/cauchy.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/cauchy.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5198,12 +5198,12 @@ <h2><span class="hidden-section">Cauchy</span><a class="headerlink" href="#cauch
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.cauchy.Cauchy.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/cauchy.py#L95"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/cauchy.py#L95"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.cauchy.Cauchy.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/cauchy.py#L81"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/cauchy.py#L81"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5218,7 +5218,7 @@ <h2><span class="hidden-section">Cauchy</span><a class="headerlink" href="#cauch
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.cauchy.Cauchy.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/cauchy.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/cauchy.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.cauchy.Cauchy.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -5243,7 +5243,7 @@ <h2><span class="hidden-section">Cauchy</span><a class="headerlink" href="#cauch
 <h2><span class="hidden-section">Chi2</span><a class="headerlink" href="#chi2" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.chi2.Chi2">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.chi2.</span></span><span class="sig-name descname"><span class="pre">Chi2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/chi2.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.chi2.Chi2" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.chi2.</span></span><span class="sig-name descname"><span class="pre">Chi2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/chi2.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.chi2.Chi2" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.gamma.Gamma" title="torch.distributions.gamma.Gamma"><code class="xref py py-class docutils literal notranslate"><span class="pre">Gamma</span></code></a></p>
 <p>Creates a Chi-squared distribution parameterized by shape parameter <a class="reference internal" href="#torch.distributions.chi2.Chi2.df" title="torch.distributions.chi2.Chi2.df"><code class="xref py py-attr docutils literal notranslate"><span class="pre">df</span></code></a>.
 This is exactly equivalent to <code class="docutils literal notranslate"><span class="pre">Gamma(alpha=0.5*df,</span> <span class="pre">beta=0.5)</span></code></p>
@@ -5270,7 +5270,7 @@ <h2><span class="hidden-section">Chi2</span><a class="headerlink" href="#chi2" t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.chi2.Chi2.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/chi2.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.chi2.Chi2.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/chi2.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.chi2.Chi2.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </dd></dl>
@@ -5280,7 +5280,7 @@ <h2><span class="hidden-section">Chi2</span><a class="headerlink" href="#chi2" t
 <h2><span class="hidden-section">ContinuousBernoulli</span><a class="headerlink" href="#continuousbernoulli" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.continuous_bernoulli.ContinuousBernoulli">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.continuous_bernoulli.</span></span><span class="sig-name descname"><span class="pre">ContinuousBernoulli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.499,</span> <span class="pre">0.501)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/continuous_bernoulli.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.continuous_bernoulli.</span></span><span class="sig-name descname"><span class="pre">ContinuousBernoulli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.499,</span> <span class="pre">0.501)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/continuous_bernoulli.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Creates a continuous Bernoulli distribution parameterized by <a class="reference internal" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.probs" title="torch.distributions.continuous_bernoulli.ContinuousBernoulli.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a>
 or <a class="reference internal" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.logits" title="torch.distributions.continuous_bernoulli.ContinuousBernoulli.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a> (but not both).</p>
@@ -5313,17 +5313,17 @@ <h2><span class="hidden-section">ContinuousBernoulli</span><a class="headerlink"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.continuous_bernoulli.ContinuousBernoulli.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/continuous_bernoulli.py#L192"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/continuous_bernoulli.py#L192"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.continuous_bernoulli.ContinuousBernoulli.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/continuous_bernoulli.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/continuous_bernoulli.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.continuous_bernoulli.ContinuousBernoulli.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/continuous_bernoulli.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/continuous_bernoulli.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5333,12 +5333,12 @@ <h2><span class="hidden-section">ContinuousBernoulli</span><a class="headerlink"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.continuous_bernoulli.ContinuousBernoulli.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/continuous_bernoulli.py#L208"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/continuous_bernoulli.py#L208"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.continuous_bernoulli.ContinuousBernoulli.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/continuous_bernoulli.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/continuous_bernoulli.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5363,7 +5363,7 @@ <h2><span class="hidden-section">ContinuousBernoulli</span><a class="headerlink"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.continuous_bernoulli.ContinuousBernoulli.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/continuous_bernoulli.py#L178"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/continuous_bernoulli.py#L178"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -5373,7 +5373,7 @@ <h2><span class="hidden-section">ContinuousBernoulli</span><a class="headerlink"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.continuous_bernoulli.ContinuousBernoulli.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/continuous_bernoulli.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/continuous_bernoulli.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.continuous_bernoulli.ContinuousBernoulli.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5398,7 +5398,7 @@ <h2><span class="hidden-section">ContinuousBernoulli</span><a class="headerlink"
 <h2><span class="hidden-section">Dirichlet</span><a class="headerlink" href="#dirichlet" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.dirichlet.Dirichlet">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.dirichlet.</span></span><span class="sig-name descname"><span class="pre">Dirichlet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/dirichlet.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.dirichlet.</span></span><span class="sig-name descname"><span class="pre">Dirichlet</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/dirichlet.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Creates a Dirichlet distribution parameterized by concentration <code class="xref py py-attr docutils literal notranslate"><span class="pre">concentration</span></code>.</p>
 <p>Example:</p>
@@ -5420,12 +5420,12 @@ <h2><span class="hidden-section">Dirichlet</span><a class="headerlink" href="#di
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.dirichlet.Dirichlet.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/dirichlet.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/dirichlet.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.dirichlet.Dirichlet.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/dirichlet.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/dirichlet.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5435,7 +5435,7 @@ <h2><span class="hidden-section">Dirichlet</span><a class="headerlink" href="#di
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.dirichlet.Dirichlet.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/dirichlet.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/dirichlet.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5450,7 +5450,7 @@ <h2><span class="hidden-section">Dirichlet</span><a class="headerlink" href="#di
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.dirichlet.Dirichlet.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/dirichlet.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/dirichlet.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.dirichlet.Dirichlet.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -5475,7 +5475,7 @@ <h2><span class="hidden-section">Dirichlet</span><a class="headerlink" href="#di
 <h2><span class="hidden-section">Exponential</span><a class="headerlink" href="#exponential" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.exponential.Exponential">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.exponential.</span></span><span class="sig-name descname"><span class="pre">Exponential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exponential.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.exponential.</span></span><span class="sig-name descname"><span class="pre">Exponential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exponential.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Creates a Exponential distribution parameterized by <code class="xref py py-attr docutils literal notranslate"><span class="pre">rate</span></code>.</p>
 <p>Example:</p>
@@ -5496,17 +5496,17 @@ <h2><span class="hidden-section">Exponential</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.exponential.Exponential.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exponential.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exponential.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.exponential.Exponential.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exponential.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exponential.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.exponential.Exponential.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exponential.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exponential.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5516,12 +5516,12 @@ <h2><span class="hidden-section">Exponential</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.exponential.Exponential.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exponential.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exponential.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.exponential.Exponential.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exponential.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exponential.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5536,7 +5536,7 @@ <h2><span class="hidden-section">Exponential</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.exponential.Exponential.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/exponential.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/exponential.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.exponential.Exponential.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -5566,7 +5566,7 @@ <h2><span class="hidden-section">Exponential</span><a class="headerlink" href="#
 <h2><span class="hidden-section">FisherSnedecor</span><a class="headerlink" href="#fishersnedecor" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.fishersnedecor.FisherSnedecor">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.fishersnedecor.</span></span><span class="sig-name descname"><span class="pre">FisherSnedecor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">df2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/fishersnedecor.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.fishersnedecor.FisherSnedecor" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.fishersnedecor.</span></span><span class="sig-name descname"><span class="pre">FisherSnedecor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">df2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/fishersnedecor.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.fishersnedecor.FisherSnedecor" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a Fisher-Snedecor distribution parameterized by <code class="xref py py-attr docutils literal notranslate"><span class="pre">df1</span></code> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">df2</span></code>.</p>
 <p>Example:</p>
@@ -5590,7 +5590,7 @@ <h2><span class="hidden-section">FisherSnedecor</span><a class="headerlink" href
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.fishersnedecor.FisherSnedecor.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/fishersnedecor.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.fishersnedecor.FisherSnedecor.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/fishersnedecor.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.fishersnedecor.FisherSnedecor.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5600,7 +5600,7 @@ <h2><span class="hidden-section">FisherSnedecor</span><a class="headerlink" href
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.fishersnedecor.FisherSnedecor.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/fishersnedecor.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.fishersnedecor.FisherSnedecor.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/fishersnedecor.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.fishersnedecor.FisherSnedecor.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5615,7 +5615,7 @@ <h2><span class="hidden-section">FisherSnedecor</span><a class="headerlink" href
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.fishersnedecor.FisherSnedecor.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/fishersnedecor.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.fishersnedecor.FisherSnedecor.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/fishersnedecor.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.fishersnedecor.FisherSnedecor.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -5640,7 +5640,7 @@ <h2><span class="hidden-section">FisherSnedecor</span><a class="headerlink" href
 <h2><span class="hidden-section">Gamma</span><a class="headerlink" href="#gamma" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.gamma.Gamma">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.gamma.</span></span><span class="sig-name descname"><span class="pre">Gamma</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gamma.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.gamma.</span></span><span class="sig-name descname"><span class="pre">Gamma</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gamma.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Creates a Gamma distribution parameterized by shape <code class="xref py py-attr docutils literal notranslate"><span class="pre">concentration</span></code> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">rate</span></code>.</p>
 <p>Example:</p>
@@ -5666,17 +5666,17 @@ <h2><span class="hidden-section">Gamma</span><a class="headerlink" href="#gamma"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.gamma.Gamma.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gamma.py#L115"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gamma.py#L115"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.gamma.Gamma.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gamma.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gamma.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.gamma.Gamma.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gamma.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gamma.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5686,7 +5686,7 @@ <h2><span class="hidden-section">Gamma</span><a class="headerlink" href="#gamma"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.gamma.Gamma.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gamma.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gamma.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5701,7 +5701,7 @@ <h2><span class="hidden-section">Gamma</span><a class="headerlink" href="#gamma"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.gamma.Gamma.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gamma.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gamma.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gamma.Gamma.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -5726,7 +5726,7 @@ <h2><span class="hidden-section">Gamma</span><a class="headerlink" href="#gamma"
 <h2><span class="hidden-section">GeneralizedPareto</span><a class="headerlink" href="#generalizedpareto" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.generalized_pareto.</span></span><span class="sig-name descname"><span class="pre">GeneralizedPareto</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.generalized_pareto.</span></span><span class="sig-name descname"><span class="pre">GeneralizedPareto</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a Generalized Pareto distribution parameterized by <code class="xref py py-attr docutils literal notranslate"><span class="pre">loc</span></code>, <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale</span></code>, and <code class="xref py py-attr docutils literal notranslate"><span class="pre">concentration</span></code>.</p>
 <p>The Generalized Pareto distribution is a family of continuous probability distributions on the real line.
@@ -5756,17 +5756,17 @@ <h2><span class="hidden-section">GeneralizedPareto</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5776,22 +5776,22 @@ <h2><span class="hidden-section">GeneralizedPareto</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L106"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L106"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto.log_cdf">
-<span class="sig-name descname"><span class="pre">log_cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.log_cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.log_cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto.log_survival_function">
-<span class="sig-name descname"><span class="pre">log_survival_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.log_survival_function" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_survival_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.log_survival_function" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5806,7 +5806,7 @@ <h2><span class="hidden-section">GeneralizedPareto</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.generalized_pareto.GeneralizedPareto.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/generalized_pareto.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/generalized_pareto.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.generalized_pareto.GeneralizedPareto.rsample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5831,7 +5831,7 @@ <h2><span class="hidden-section">GeneralizedPareto</span><a class="headerlink" h
 <h2><span class="hidden-section">Geometric</span><a class="headerlink" href="#geometric" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.geometric.Geometric">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.geometric.</span></span><span class="sig-name descname"><span class="pre">Geometric</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/geometric.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.geometric.</span></span><span class="sig-name descname"><span class="pre">Geometric</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/geometric.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a Geometric distribution parameterized by <a class="reference internal" href="#torch.distributions.geometric.Geometric.probs" title="torch.distributions.geometric.Geometric.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a>,
 where <a class="reference internal" href="#torch.distributions.geometric.Geometric.probs" title="torch.distributions.geometric.Geometric.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a> is the probability of success of Bernoulli trials.</p>
@@ -5863,17 +5863,17 @@ <h2><span class="hidden-section">Geometric</span><a class="headerlink" href="#ge
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.geometric.Geometric.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/geometric.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/geometric.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.geometric.Geometric.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/geometric.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/geometric.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.geometric.Geometric.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/geometric.py#L128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/geometric.py#L128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5898,7 +5898,7 @@ <h2><span class="hidden-section">Geometric</span><a class="headerlink" href="#ge
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.geometric.Geometric.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/geometric.py#L116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/geometric.py#L116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.geometric.Geometric.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5918,7 +5918,7 @@ <h2><span class="hidden-section">Geometric</span><a class="headerlink" href="#ge
 <h2><span class="hidden-section">Gumbel</span><a class="headerlink" href="#gumbel" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.gumbel.Gumbel">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.gumbel.</span></span><span class="sig-name descname"><span class="pre">Gumbel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gumbel.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gumbel.Gumbel" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.gumbel.</span></span><span class="sig-name descname"><span class="pre">Gumbel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gumbel.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gumbel.Gumbel" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Samples from a Gumbel Distribution.</p>
 <p>Examples:</p>
@@ -5942,17 +5942,17 @@ <h2><span class="hidden-section">Gumbel</span><a class="headerlink" href="#gumbe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.gumbel.Gumbel.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gumbel.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gumbel.Gumbel.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gumbel.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gumbel.Gumbel.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.gumbel.Gumbel.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gumbel.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gumbel.Gumbel.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gumbel.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gumbel.Gumbel.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.gumbel.Gumbel.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/gumbel.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gumbel.Gumbel.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/gumbel.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.gumbel.Gumbel.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5987,7 +5987,7 @@ <h2><span class="hidden-section">Gumbel</span><a class="headerlink" href="#gumbe
 <h2><span class="hidden-section">HalfCauchy</span><a class="headerlink" href="#halfcauchy" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.half_cauchy.HalfCauchy">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.half_cauchy.</span></span><span class="sig-name descname"><span class="pre">HalfCauchy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_cauchy.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.half_cauchy.</span></span><span class="sig-name descname"><span class="pre">HalfCauchy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_cauchy.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Creates a half-Cauchy distribution parameterized by <cite>scale</cite> where:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">X</span> <span class="o">~</span> <span class="n">Cauchy</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">scale</span><span class="p">)</span>
@@ -6017,17 +6017,17 @@ <h2><span class="hidden-section">HalfCauchy</span><a class="headerlink" href="#h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_cauchy.HalfCauchy.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_cauchy.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_cauchy.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_cauchy.HalfCauchy.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_cauchy.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_cauchy.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_cauchy.HalfCauchy.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_cauchy.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_cauchy.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6037,12 +6037,12 @@ <h2><span class="hidden-section">HalfCauchy</span><a class="headerlink" href="#h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_cauchy.HalfCauchy.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prob</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_cauchy.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prob</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_cauchy.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_cauchy.HalfCauchy.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_cauchy.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_cauchy.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_cauchy.HalfCauchy.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6077,7 +6077,7 @@ <h2><span class="hidden-section">HalfCauchy</span><a class="headerlink" href="#h
 <h2><span class="hidden-section">HalfNormal</span><a class="headerlink" href="#halfnormal" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.half_normal.HalfNormal">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.half_normal.</span></span><span class="sig-name descname"><span class="pre">HalfNormal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_normal.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.half_normal.</span></span><span class="sig-name descname"><span class="pre">HalfNormal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_normal.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Creates a half-normal distribution parameterized by <cite>scale</cite> where:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">X</span> <span class="o">~</span> <span class="n">Normal</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">scale</span><span class="p">)</span>
@@ -6107,17 +6107,17 @@ <h2><span class="hidden-section">HalfNormal</span><a class="headerlink" href="#h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_normal.HalfNormal.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_normal.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_normal.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_normal.HalfNormal.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_normal.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_normal.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_normal.HalfNormal.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_normal.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_normal.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6127,12 +6127,12 @@ <h2><span class="hidden-section">HalfNormal</span><a class="headerlink" href="#h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_normal.HalfNormal.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prob</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_normal.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prob</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_normal.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.half_normal.HalfNormal.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/half_normal.py#L67"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/half_normal.py#L67"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.half_normal.HalfNormal.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6167,7 +6167,7 @@ <h2><span class="hidden-section">HalfNormal</span><a class="headerlink" href="#h
 <h2><span class="hidden-section">Independent</span><a class="headerlink" href="#independent" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.independent.Independent">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.independent.</span></span><span class="sig-name descname"><span class="pre">Independent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reinterpreted_batch_ndims</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/independent.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.independent.</span></span><span class="sig-name descname"><span class="pre">Independent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reinterpreted_batch_ndims</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/independent.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a>, <a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Generic" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Generic</span></code></a>[<code class="xref py py-obj docutils literal notranslate"><span class="pre">D</span></code>]</p>
 <p>Reinterprets some of the batch dims of a distribution as event dims.</p>
 <p>This is mainly useful for changing the shape of the result of
@@ -6211,17 +6211,17 @@ <h2><span class="hidden-section">Independent</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.independent.Independent.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/independent.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/independent.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.independent.Independent.enumerate_support">
-<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/independent.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.enumerate_support" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/independent.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.enumerate_support" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.independent.Independent.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/independent.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/independent.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6236,7 +6236,7 @@ <h2><span class="hidden-section">Independent</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.independent.Independent.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/independent.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/independent.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6251,7 +6251,7 @@ <h2><span class="hidden-section">Independent</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.independent.Independent.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/independent.py#L115"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/independent.py#L115"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -6261,7 +6261,7 @@ <h2><span class="hidden-section">Independent</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.independent.Independent.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/independent.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/independent.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.independent.Independent.sample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -6291,7 +6291,7 @@ <h2><span class="hidden-section">Independent</span><a class="headerlink" href="#
 <h2><span class="hidden-section">InverseGamma</span><a class="headerlink" href="#inversegamma" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.inverse_gamma.InverseGamma">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.inverse_gamma.</span></span><span class="sig-name descname"><span class="pre">InverseGamma</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/inverse_gamma.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.inverse_gamma.InverseGamma" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.inverse_gamma.</span></span><span class="sig-name descname"><span class="pre">InverseGamma</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/inverse_gamma.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.inverse_gamma.InverseGamma" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Creates an inverse gamma distribution parameterized by <a class="reference internal" href="#torch.distributions.inverse_gamma.InverseGamma.concentration" title="torch.distributions.inverse_gamma.InverseGamma.concentration"><code class="xref py py-attr docutils literal notranslate"><span class="pre">concentration</span></code></a> and <a class="reference internal" href="#torch.distributions.inverse_gamma.InverseGamma.rate" title="torch.distributions.inverse_gamma.InverseGamma.rate"><code class="xref py py-attr docutils literal notranslate"><span class="pre">rate</span></code></a>
 where:</p>
@@ -6332,12 +6332,12 @@ <h2><span class="hidden-section">InverseGamma</span><a class="headerlink" href="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.inverse_gamma.InverseGamma.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/inverse_gamma.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.inverse_gamma.InverseGamma.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/inverse_gamma.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.inverse_gamma.InverseGamma.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.inverse_gamma.InverseGamma.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/inverse_gamma.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.inverse_gamma.InverseGamma.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/inverse_gamma.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.inverse_gamma.InverseGamma.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6377,7 +6377,7 @@ <h2><span class="hidden-section">InverseGamma</span><a class="headerlink" href="
 <h2><span class="hidden-section">Kumaraswamy</span><a class="headerlink" href="#kumaraswamy" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.kumaraswamy.Kumaraswamy">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.kumaraswamy.</span></span><span class="sig-name descname"><span class="pre">Kumaraswamy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/kumaraswamy.py#L25"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kumaraswamy.Kumaraswamy" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.kumaraswamy.</span></span><span class="sig-name descname"><span class="pre">Kumaraswamy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">concentration1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/kumaraswamy.py#L25"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kumaraswamy.Kumaraswamy" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Samples from a Kumaraswamy distribution.</p>
 <p>Example:</p>
@@ -6403,12 +6403,12 @@ <h2><span class="hidden-section">Kumaraswamy</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.kumaraswamy.Kumaraswamy.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/kumaraswamy.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kumaraswamy.Kumaraswamy.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/kumaraswamy.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kumaraswamy.Kumaraswamy.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.kumaraswamy.Kumaraswamy.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/kumaraswamy.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kumaraswamy.Kumaraswamy.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/kumaraswamy.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kumaraswamy.Kumaraswamy.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6443,7 +6443,7 @@ <h2><span class="hidden-section">Kumaraswamy</span><a class="headerlink" href="#
 <h2><span class="hidden-section">LKJCholesky</span><a class="headerlink" href="#lkjcholesky" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.lkj_cholesky.LKJCholesky">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.lkj_cholesky.</span></span><span class="sig-name descname"><span class="pre">LKJCholesky</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lkj_cholesky.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lkj_cholesky.LKJCholesky" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.lkj_cholesky.</span></span><span class="sig-name descname"><span class="pre">LKJCholesky</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lkj_cholesky.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lkj_cholesky.LKJCholesky" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>LKJ distribution for lower Cholesky factor of correlation matrices.
 The distribution is controlled by <code class="docutils literal notranslate"><span class="pre">concentration</span></code> parameter <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>η</mi></mrow><annotation encoding="application/x-tex">\eta</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">η</span></span></span></span></span>
@@ -6488,17 +6488,17 @@ <h2><span class="hidden-section">LKJCholesky</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.lkj_cholesky.LKJCholesky.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lkj_cholesky.py#L93"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lkj_cholesky.LKJCholesky.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lkj_cholesky.py#L93"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lkj_cholesky.LKJCholesky.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.lkj_cholesky.LKJCholesky.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lkj_cholesky.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lkj_cholesky.LKJCholesky.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lkj_cholesky.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lkj_cholesky.LKJCholesky.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.lkj_cholesky.LKJCholesky.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lkj_cholesky.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lkj_cholesky.LKJCholesky.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lkj_cholesky.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lkj_cholesky.LKJCholesky.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6513,7 +6513,7 @@ <h2><span class="hidden-section">LKJCholesky</span><a class="headerlink" href="#
 <h2><span class="hidden-section">Laplace</span><a class="headerlink" href="#laplace" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.laplace.Laplace">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.laplace.</span></span><span class="sig-name descname"><span class="pre">Laplace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/laplace.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.laplace.</span></span><span class="sig-name descname"><span class="pre">Laplace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/laplace.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a Laplace distribution parameterized by <code class="xref py py-attr docutils literal notranslate"><span class="pre">loc</span></code> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale</span></code>.</p>
 <p>Example:</p>
@@ -6537,17 +6537,17 @@ <h2><span class="hidden-section">Laplace</span><a class="headerlink" href="#lapl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.laplace.Laplace.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/laplace.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/laplace.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.laplace.Laplace.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/laplace.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/laplace.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.laplace.Laplace.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/laplace.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/laplace.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6557,12 +6557,12 @@ <h2><span class="hidden-section">Laplace</span><a class="headerlink" href="#lapl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.laplace.Laplace.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/laplace.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/laplace.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.laplace.Laplace.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/laplace.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/laplace.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6577,7 +6577,7 @@ <h2><span class="hidden-section">Laplace</span><a class="headerlink" href="#lapl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.laplace.Laplace.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/laplace.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/laplace.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.laplace.Laplace.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -6607,7 +6607,7 @@ <h2><span class="hidden-section">Laplace</span><a class="headerlink" href="#lapl
 <h2><span class="hidden-section">LogNormal</span><a class="headerlink" href="#lognormal" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.log_normal.LogNormal">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.log_normal.</span></span><span class="sig-name descname"><span class="pre">LogNormal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/log_normal.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.log_normal.LogNormal" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.log_normal.</span></span><span class="sig-name descname"><span class="pre">LogNormal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/log_normal.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.log_normal.LogNormal" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Creates a log-normal distribution parameterized by
 <a class="reference internal" href="#torch.distributions.log_normal.LogNormal.loc" title="torch.distributions.log_normal.LogNormal.loc"><code class="xref py py-attr docutils literal notranslate"><span class="pre">loc</span></code></a> and <a class="reference internal" href="#torch.distributions.log_normal.LogNormal.scale" title="torch.distributions.log_normal.LogNormal.scale"><code class="xref py py-attr docutils literal notranslate"><span class="pre">scale</span></code></a> where:</p>
@@ -6641,12 +6641,12 @@ <h2><span class="hidden-section">LogNormal</span><a class="headerlink" href="#lo
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.log_normal.LogNormal.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/log_normal.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.log_normal.LogNormal.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/log_normal.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.log_normal.LogNormal.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.log_normal.LogNormal.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/log_normal.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.log_normal.LogNormal.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/log_normal.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.log_normal.LogNormal.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6691,7 +6691,7 @@ <h2><span class="hidden-section">LogNormal</span><a class="headerlink" href="#lo
 <h2><span class="hidden-section">LowRankMultivariateNormal</span><a class="headerlink" href="#lowrankmultivariatenormal" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.lowrank_multivariate_normal.</span></span><span class="sig-name descname"><span class="pre">LowRankMultivariateNormal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cov_factor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cov_diag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lowrank_multivariate_normal.py#L55"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.lowrank_multivariate_normal.</span></span><span class="sig-name descname"><span class="pre">LowRankMultivariateNormal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cov_factor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cov_diag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lowrank_multivariate_normal.py#L55"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a multivariate normal distribution with covariance matrix having a low-rank form
 parameterized by <code class="xref py py-attr docutils literal notranslate"><span class="pre">cov_factor</span></code> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">cov_diag</span></code>:</p>
@@ -6740,12 +6740,12 @@ <h2><span class="hidden-section">LowRankMultivariateNormal</span><a class="heade
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lowrank_multivariate_normal.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lowrank_multivariate_normal.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lowrank_multivariate_normal.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lowrank_multivariate_normal.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6755,7 +6755,7 @@ <h2><span class="hidden-section">LowRankMultivariateNormal</span><a class="heade
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lowrank_multivariate_normal.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lowrank_multivariate_normal.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6775,7 +6775,7 @@ <h2><span class="hidden-section">LowRankMultivariateNormal</span><a class="heade
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/lowrank_multivariate_normal.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/lowrank_multivariate_normal.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.lowrank_multivariate_normal.LowRankMultivariateNormal.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -6805,7 +6805,7 @@ <h2><span class="hidden-section">LowRankMultivariateNormal</span><a class="heade
 <h2><span class="hidden-section">MixtureSameFamily</span><a class="headerlink" href="#mixturesamefamily" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.mixture_same_family.MixtureSameFamily">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.mixture_same_family.</span></span><span class="sig-name descname"><span class="pre">MixtureSameFamily</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mixture_distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">component_distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/mixture_same_family.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.mixture_same_family.</span></span><span class="sig-name descname"><span class="pre">MixtureSameFamily</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mixture_distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">component_distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/mixture_same_family.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>The <cite>MixtureSameFamily</cite> distribution implements a (batch of) mixture
 distribution where all component are from different parameterizations of
@@ -6856,7 +6856,7 @@ <h2><span class="hidden-section">MixtureSameFamily</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.mixture_same_family.MixtureSameFamily.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/mixture_same_family.py#L158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/mixture_same_family.py#L158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6866,7 +6866,7 @@ <h2><span class="hidden-section">MixtureSameFamily</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.mixture_same_family.MixtureSameFamily.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/mixture_same_family.py#L109"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/mixture_same_family.py#L109"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -6876,7 +6876,7 @@ <h2><span class="hidden-section">MixtureSameFamily</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.mixture_same_family.MixtureSameFamily.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/mixture_same_family.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/mixture_same_family.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6891,7 +6891,7 @@ <h2><span class="hidden-section">MixtureSameFamily</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.mixture_same_family.MixtureSameFamily.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/mixture_same_family.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/mixture_same_family.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.mixture_same_family.MixtureSameFamily.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6916,7 +6916,7 @@ <h2><span class="hidden-section">MixtureSameFamily</span><a class="headerlink" h
 <h2><span class="hidden-section">Multinomial</span><a class="headerlink" href="#multinomial" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.multinomial.Multinomial">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.multinomial.</span></span><span class="sig-name descname"><span class="pre">Multinomial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">total_count</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multinomial.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.multinomial.</span></span><span class="sig-name descname"><span class="pre">Multinomial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">total_count</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multinomial.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a Multinomial distribution parameterized by <a class="reference internal" href="#torch.distributions.multinomial.Multinomial.total_count" title="torch.distributions.multinomial.Multinomial.total_count"><code class="xref py py-attr docutils literal notranslate"><span class="pre">total_count</span></code></a> and
 either <a class="reference internal" href="#torch.distributions.multinomial.Multinomial.probs" title="torch.distributions.multinomial.Multinomial.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a> or <a class="reference internal" href="#torch.distributions.multinomial.Multinomial.logits" title="torch.distributions.multinomial.Multinomial.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a> (but not both). The innermost dimension of
@@ -6964,17 +6964,17 @@ <h2><span class="hidden-section">Multinomial</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.multinomial.Multinomial.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multinomial.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multinomial.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.multinomial.Multinomial.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multinomial.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multinomial.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.multinomial.Multinomial.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multinomial.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multinomial.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -6999,7 +6999,7 @@ <h2><span class="hidden-section">Multinomial</span><a class="headerlink" href="#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.multinomial.Multinomial.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multinomial.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multinomial.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multinomial.Multinomial.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7029,7 +7029,7 @@ <h2><span class="hidden-section">Multinomial</span><a class="headerlink" href="#
 <h2><span class="hidden-section">MultivariateNormal</span><a class="headerlink" href="#multivariatenormal" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.multivariate_normal.MultivariateNormal">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.multivariate_normal.</span></span><span class="sig-name descname"><span class="pre">MultivariateNormal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">covariance_matrix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">precision_matrix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_tril</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multivariate_normal.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.multivariate_normal.</span></span><span class="sig-name descname"><span class="pre">MultivariateNormal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">covariance_matrix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">precision_matrix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_tril</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multivariate_normal.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a multivariate normal (also called Gaussian) distribution
 parameterized by a mean vector and a covariance matrix.</p>
@@ -7077,12 +7077,12 @@ <h2><span class="hidden-section">MultivariateNormal</span><a class="headerlink"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.multivariate_normal.MultivariateNormal.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multivariate_normal.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multivariate_normal.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.multivariate_normal.MultivariateNormal.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multivariate_normal.py#L193"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multivariate_normal.py#L193"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7092,7 +7092,7 @@ <h2><span class="hidden-section">MultivariateNormal</span><a class="headerlink"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.multivariate_normal.MultivariateNormal.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multivariate_normal.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multivariate_normal.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7112,7 +7112,7 @@ <h2><span class="hidden-section">MultivariateNormal</span><a class="headerlink"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.multivariate_normal.MultivariateNormal.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/multivariate_normal.py#L246"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/multivariate_normal.py#L246"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.multivariate_normal.MultivariateNormal.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -7142,7 +7142,7 @@ <h2><span class="hidden-section">MultivariateNormal</span><a class="headerlink"
 <h2><span class="hidden-section">NegativeBinomial</span><a class="headerlink" href="#negativebinomial" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.negative_binomial.NegativeBinomial">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.negative_binomial.</span></span><span class="sig-name descname"><span class="pre">NegativeBinomial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">total_count</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/negative_binomial.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.negative_binomial.NegativeBinomial" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.negative_binomial.</span></span><span class="sig-name descname"><span class="pre">NegativeBinomial</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">total_count</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/negative_binomial.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.negative_binomial.NegativeBinomial" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a Negative Binomial distribution, i.e. distribution
 of the number of successful independent and identical Bernoulli trials
@@ -7166,12 +7166,12 @@ <h2><span class="hidden-section">NegativeBinomial</span><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.negative_binomial.NegativeBinomial.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/negative_binomial.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.negative_binomial.NegativeBinomial.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/negative_binomial.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.negative_binomial.NegativeBinomial.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.negative_binomial.NegativeBinomial.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/negative_binomial.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.negative_binomial.NegativeBinomial.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/negative_binomial.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.negative_binomial.NegativeBinomial.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7201,7 +7201,7 @@ <h2><span class="hidden-section">NegativeBinomial</span><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.negative_binomial.NegativeBinomial.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/negative_binomial.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.negative_binomial.NegativeBinomial.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/negative_binomial.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.negative_binomial.NegativeBinomial.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7221,7 +7221,7 @@ <h2><span class="hidden-section">NegativeBinomial</span><a class="headerlink" hr
 <h2><span class="hidden-section">Normal</span><a class="headerlink" href="#normal" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.normal.Normal">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.normal.</span></span><span class="sig-name descname"><span class="pre">Normal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/normal.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.normal.</span></span><span class="sig-name descname"><span class="pre">Normal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/normal.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Creates a normal (also called Gaussian) distribution parameterized by
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">loc</span></code> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale</span></code>.</p>
@@ -7247,17 +7247,17 @@ <h2><span class="hidden-section">Normal</span><a class="headerlink" href="#norma
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.normal.Normal.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/normal.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/normal.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.normal.Normal.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/normal.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/normal.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.normal.Normal.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/normal.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/normal.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7267,12 +7267,12 @@ <h2><span class="hidden-section">Normal</span><a class="headerlink" href="#norma
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.normal.Normal.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/normal.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/normal.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.normal.Normal.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/normal.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/normal.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7287,7 +7287,7 @@ <h2><span class="hidden-section">Normal</span><a class="headerlink" href="#norma
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.normal.Normal.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/normal.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/normal.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -7297,7 +7297,7 @@ <h2><span class="hidden-section">Normal</span><a class="headerlink" href="#norma
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.normal.Normal.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/normal.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/normal.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.normal.Normal.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7322,7 +7322,7 @@ <h2><span class="hidden-section">Normal</span><a class="headerlink" href="#norma
 <h2><span class="hidden-section">OneHotCategorical</span><a class="headerlink" href="#onehotcategorical" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.one_hot_categorical.OneHotCategorical">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.one_hot_categorical.</span></span><span class="sig-name descname"><span class="pre">OneHotCategorical</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/one_hot_categorical.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.one_hot_categorical.</span></span><span class="sig-name descname"><span class="pre">OneHotCategorical</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/one_hot_categorical.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a one-hot categorical distribution parameterized by <a class="reference internal" href="#torch.distributions.one_hot_categorical.OneHotCategorical.probs" title="torch.distributions.one_hot_categorical.OneHotCategorical.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a> or
 <a class="reference internal" href="#torch.distributions.one_hot_categorical.OneHotCategorical.logits" title="torch.distributions.one_hot_categorical.OneHotCategorical.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a>.</p>
@@ -7360,17 +7360,17 @@ <h2><span class="hidden-section">OneHotCategorical</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.one_hot_categorical.OneHotCategorical.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/one_hot_categorical.py#L116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/one_hot_categorical.py#L116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.one_hot_categorical.OneHotCategorical.enumerate_support">
-<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/one_hot_categorical.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.enumerate_support" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">enumerate_support</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expand</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/one_hot_categorical.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.enumerate_support" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.one_hot_categorical.OneHotCategorical.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/one_hot_categorical.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/one_hot_categorical.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7380,7 +7380,7 @@ <h2><span class="hidden-section">OneHotCategorical</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.one_hot_categorical.OneHotCategorical.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/one_hot_categorical.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/one_hot_categorical.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7410,7 +7410,7 @@ <h2><span class="hidden-section">OneHotCategorical</span><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.one_hot_categorical.OneHotCategorical.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/one_hot_categorical.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/one_hot_categorical.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.one_hot_categorical.OneHotCategorical.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7430,7 +7430,7 @@ <h2><span class="hidden-section">OneHotCategorical</span><a class="headerlink" h
 <h2><span class="hidden-section">Pareto</span><a class="headerlink" href="#pareto" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.pareto.Pareto">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.pareto.</span></span><span class="sig-name descname"><span class="pre">Pareto</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/pareto.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.pareto.Pareto" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.pareto.</span></span><span class="sig-name descname"><span class="pre">Pareto</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/pareto.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.pareto.Pareto" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Samples from a Pareto Type 1 distribution.</p>
 <p>Example:</p>
@@ -7454,7 +7454,7 @@ <h2><span class="hidden-section">Pareto</span><a class="headerlink" href="#paret
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.pareto.Pareto.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/pareto.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.pareto.Pareto.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/pareto.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.pareto.Pareto.entropy" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -7464,7 +7464,7 @@ <h2><span class="hidden-section">Pareto</span><a class="headerlink" href="#paret
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.pareto.Pareto.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/pareto.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.pareto.Pareto.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/pareto.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.pareto.Pareto.expand" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="#torch.distributions.pareto.Pareto" title="torch.distributions.pareto.Pareto"><em>Pareto</em></a></p>
@@ -7504,7 +7504,7 @@ <h2><span class="hidden-section">Pareto</span><a class="headerlink" href="#paret
 <h2><span class="hidden-section">Poisson</span><a class="headerlink" href="#poisson" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.poisson.Poisson">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.poisson.</span></span><span class="sig-name descname"><span class="pre">Poisson</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/poisson.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.poisson.Poisson" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.poisson.</span></span><span class="sig-name descname"><span class="pre">Poisson</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rate</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/poisson.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.poisson.Poisson" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Creates a Poisson distribution parameterized by <code class="xref py py-attr docutils literal notranslate"><span class="pre">rate</span></code>, the rate parameter.</p>
 <p>Samples are nonnegative integers, with a pmf given by</p>
@@ -7529,12 +7529,12 @@ <h2><span class="hidden-section">Poisson</span><a class="headerlink" href="#pois
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.poisson.Poisson.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/poisson.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.poisson.Poisson.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/poisson.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.poisson.Poisson.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.poisson.Poisson.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/poisson.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.poisson.Poisson.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/poisson.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.poisson.Poisson.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7549,7 +7549,7 @@ <h2><span class="hidden-section">Poisson</span><a class="headerlink" href="#pois
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.poisson.Poisson.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/poisson.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.poisson.Poisson.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/poisson.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.poisson.Poisson.sample" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7569,7 +7569,7 @@ <h2><span class="hidden-section">Poisson</span><a class="headerlink" href="#pois
 <h2><span class="hidden-section">RelaxedBernoulli</span><a class="headerlink" href="#relaxedbernoulli" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.relaxed_bernoulli.RelaxedBernoulli">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.relaxed_bernoulli.</span></span><span class="sig-name descname"><span class="pre">RelaxedBernoulli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">temperature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/relaxed_bernoulli.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.RelaxedBernoulli" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.relaxed_bernoulli.</span></span><span class="sig-name descname"><span class="pre">RelaxedBernoulli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">temperature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/relaxed_bernoulli.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.RelaxedBernoulli" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Creates a RelaxedBernoulli distribution, parametrized by
 <a class="reference internal" href="#torch.distributions.relaxed_bernoulli.RelaxedBernoulli.temperature" title="torch.distributions.relaxed_bernoulli.RelaxedBernoulli.temperature"><code class="xref py py-attr docutils literal notranslate"><span class="pre">temperature</span></code></a>, and either <a class="reference internal" href="#torch.distributions.relaxed_bernoulli.RelaxedBernoulli.probs" title="torch.distributions.relaxed_bernoulli.RelaxedBernoulli.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a> or <a class="reference internal" href="#torch.distributions.relaxed_bernoulli.RelaxedBernoulli.logits" title="torch.distributions.relaxed_bernoulli.RelaxedBernoulli.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a>
@@ -7603,7 +7603,7 @@ <h2><span class="hidden-section">RelaxedBernoulli</span><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.relaxed_bernoulli.RelaxedBernoulli.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/relaxed_bernoulli.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.RelaxedBernoulli.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/relaxed_bernoulli.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.RelaxedBernoulli.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7638,7 +7638,7 @@ <h2><span class="hidden-section">RelaxedBernoulli</span><a class="headerlink" hr
 <h2><span class="hidden-section">LogitRelaxedBernoulli</span><a class="headerlink" href="#logitrelaxedbernoulli" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.relaxed_bernoulli.</span></span><span class="sig-name descname"><span class="pre">LogitRelaxedBernoulli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">temperature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/relaxed_bernoulli.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.relaxed_bernoulli.</span></span><span class="sig-name descname"><span class="pre">LogitRelaxedBernoulli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">temperature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/relaxed_bernoulli.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a LogitRelaxedBernoulli distribution parameterized by <a class="reference internal" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.probs" title="torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a>
 or <a class="reference internal" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.logits" title="torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a> (but not both), which is the logit of a RelaxedBernoulli
@@ -7664,12 +7664,12 @@ <h2><span class="hidden-section">LogitRelaxedBernoulli</span><a class="headerlin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/relaxed_bernoulli.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/relaxed_bernoulli.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/relaxed_bernoulli.py#L111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/relaxed_bernoulli.py#L111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7689,7 +7689,7 @@ <h2><span class="hidden-section">LogitRelaxedBernoulli</span><a class="headerlin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/relaxed_bernoulli.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/relaxed_bernoulli.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_bernoulli.LogitRelaxedBernoulli.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -7709,7 +7709,7 @@ <h2><span class="hidden-section">LogitRelaxedBernoulli</span><a class="headerlin
 <h2><span class="hidden-section">RelaxedOneHotCategorical</span><a class="headerlink" href="#relaxedonehotcategorical" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.relaxed_categorical.RelaxedOneHotCategorical">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.relaxed_categorical.</span></span><span class="sig-name descname"><span class="pre">RelaxedOneHotCategorical</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">temperature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/relaxed_categorical.py#L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_categorical.RelaxedOneHotCategorical" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.relaxed_categorical.</span></span><span class="sig-name descname"><span class="pre">RelaxedOneHotCategorical</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">temperature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">probs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/relaxed_categorical.py#L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_categorical.RelaxedOneHotCategorical" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Creates a RelaxedOneHotCategorical distribution parametrized by
 <a class="reference internal" href="#torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.temperature" title="torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.temperature"><code class="xref py py-attr docutils literal notranslate"><span class="pre">temperature</span></code></a>, and either <a class="reference internal" href="#torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.probs" title="torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.probs"><code class="xref py py-attr docutils literal notranslate"><span class="pre">probs</span></code></a> or <a class="reference internal" href="#torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.logits" title="torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.logits"><code class="xref py py-attr docutils literal notranslate"><span class="pre">logits</span></code></a>.
@@ -7743,7 +7743,7 @@ <h2><span class="hidden-section">RelaxedOneHotCategorical</span><a class="header
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/relaxed_categorical.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/relaxed_categorical.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.relaxed_categorical.RelaxedOneHotCategorical.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7778,7 +7778,7 @@ <h2><span class="hidden-section">RelaxedOneHotCategorical</span><a class="header
 <h2><span class="hidden-section">StudentT</span><a class="headerlink" href="#studentt" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.studentT.StudentT">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.studentT.</span></span><span class="sig-name descname"><span class="pre">StudentT</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loc</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/studentT.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.studentT.</span></span><span class="sig-name descname"><span class="pre">StudentT</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loc</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/studentT.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Creates a Student’s t-distribution parameterized by degree of
 freedom <code class="xref py py-attr docutils literal notranslate"><span class="pre">df</span></code>, mean <code class="xref py py-attr docutils literal notranslate"><span class="pre">loc</span></code> and scale <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale</span></code>.</p>
@@ -7804,12 +7804,12 @@ <h2><span class="hidden-section">StudentT</span><a class="headerlink" href="#stu
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.studentT.StudentT.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/studentT.py#L114"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/studentT.py#L114"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.studentT.StudentT.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/studentT.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/studentT.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -7819,7 +7819,7 @@ <h2><span class="hidden-section">StudentT</span><a class="headerlink" href="#stu
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.studentT.StudentT.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/studentT.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/studentT.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7834,7 +7834,7 @@ <h2><span class="hidden-section">StudentT</span><a class="headerlink" href="#stu
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.studentT.StudentT.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/studentT.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/studentT.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.studentT.StudentT.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -7859,7 +7859,7 @@ <h2><span class="hidden-section">StudentT</span><a class="headerlink" href="#stu
 <h2><span class="hidden-section">TransformedDistribution</span><a class="headerlink" href="#transformeddistribution" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transformed_distribution.TransformedDistribution">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transformed_distribution.</span></span><span class="sig-name descname"><span class="pre">TransformedDistribution</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transforms</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transformed_distribution.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transformed_distribution.</span></span><span class="sig-name descname"><span class="pre">TransformedDistribution</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transforms</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transformed_distribution.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Extension of the Distribution class, which applies a sequence of Transforms
 to a base distribution.  Let f be the composition of transforms applied:</p>
@@ -7899,14 +7899,14 @@ <h2><span class="hidden-section">TransformedDistribution</span><a class="headerl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transformed_distribution.TransformedDistribution.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transformed_distribution.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transformed_distribution.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.cdf" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the cumulative distribution function by inverting the
 transform(s) and computing the score of the base distribution.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transformed_distribution.TransformedDistribution.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transformed_distribution.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transformed_distribution.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -7916,21 +7916,21 @@ <h2><span class="hidden-section">TransformedDistribution</span><a class="headerl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transformed_distribution.TransformedDistribution.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transformed_distribution.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transformed_distribution.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.icdf" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the inverse cumulative distribution function using
 transform(s) and computing the score of the base distribution.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transformed_distribution.TransformedDistribution.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transformed_distribution.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transformed_distribution.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.log_prob" title="Permalink to this definition">#</a></dt>
 <dd><p>Scores the sample by inverting the transform(s) and computing the score
 using the score of the base distribution and the log abs det jacobian.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transformed_distribution.TransformedDistribution.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transformed_distribution.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transformed_distribution.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.rsample" title="Permalink to this definition">#</a></dt>
 <dd><p>Generates a sample_shape shaped reparameterized sample or sample_shape
 shaped batch of reparameterized samples if the distribution parameters
 are batched. Samples first from base distribution and applies
@@ -7944,7 +7944,7 @@ <h2><span class="hidden-section">TransformedDistribution</span><a class="headerl
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transformed_distribution.TransformedDistribution.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transformed_distribution.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transformed_distribution.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transformed_distribution.TransformedDistribution.sample" title="Permalink to this definition">#</a></dt>
 <dd><p>Generates a sample_shape shaped sample or sample_shape shaped batch of
 samples if the distribution parameters are batched. Samples first from
 base distribution and applies <cite>transform()</cite> for every transform in the
@@ -7968,7 +7968,7 @@ <h2><span class="hidden-section">TransformedDistribution</span><a class="headerl
 <h2><span class="hidden-section">Uniform</span><a class="headerlink" href="#uniform" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.uniform.Uniform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.uniform.</span></span><span class="sig-name descname"><span class="pre">Uniform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">low</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">high</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/uniform.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.uniform.</span></span><span class="sig-name descname"><span class="pre">Uniform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">low</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">high</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/uniform.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>Generates uniformly distributed random samples from the half-open interval
 <code class="docutils literal notranslate"><span class="pre">[low,</span> <span class="pre">high)</span></code>.</p>
@@ -7993,17 +7993,17 @@ <h2><span class="hidden-section">Uniform</span><a class="headerlink" href="#unif
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.uniform.Uniform.cdf">
-<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/uniform.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.cdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/uniform.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.cdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.uniform.Uniform.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/uniform.py#L107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/uniform.py#L107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.uniform.Uniform.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/uniform.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/uniform.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -8013,12 +8013,12 @@ <h2><span class="hidden-section">Uniform</span><a class="headerlink" href="#unif
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.uniform.Uniform.icdf">
-<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/uniform.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.icdf" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">icdf</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/uniform.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.icdf" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.uniform.Uniform.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/uniform.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/uniform.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -8033,7 +8033,7 @@ <h2><span class="hidden-section">Uniform</span><a class="headerlink" href="#unif
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.uniform.Uniform.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/uniform.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/uniform.py#L85"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.uniform.Uniform.rsample" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><em>Tensor</em></a></p>
@@ -8068,7 +8068,7 @@ <h2><span class="hidden-section">Uniform</span><a class="headerlink" href="#unif
 <h2><span class="hidden-section">VonMises</span><a class="headerlink" href="#vonmises" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.von_mises.VonMises">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.von_mises.</span></span><span class="sig-name descname"><span class="pre">VonMises</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/von_mises.py#L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.von_mises.VonMises" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.von_mises.</span></span><span class="sig-name descname"><span class="pre">VonMises</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/von_mises.py#L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.von_mises.VonMises" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.distribution.Distribution" title="torch.distributions.distribution.Distribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">Distribution</span></code></a></p>
 <p>A circular von Mises distribution.</p>
 <p>This implementation uses polar coordinates. The <code class="docutils literal notranslate"><span class="pre">loc</span></code> and <code class="docutils literal notranslate"><span class="pre">value</span></code> args
@@ -8097,7 +8097,7 @@ <h2><span class="hidden-section">VonMises</span><a class="headerlink" href="#von
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.von_mises.VonMises.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/von_mises.py#L187"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.von_mises.VonMises.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/von_mises.py#L187"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.von_mises.VonMises.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -8107,7 +8107,7 @@ <h2><span class="hidden-section">VonMises</span><a class="headerlink" href="#von
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.von_mises.VonMises.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/von_mises.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.von_mises.VonMises.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/von_mises.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.von_mises.VonMises.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -8123,7 +8123,7 @@ <h2><span class="hidden-section">VonMises</span><a class="headerlink" href="#von
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.von_mises.VonMises.sample">
-<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/von_mises.py#L170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.von_mises.VonMises.sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/von_mises.py#L170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.von_mises.VonMises.sample" title="Permalink to this definition">#</a></dt>
 <dd><p>The sampling algorithm for the von Mises distribution is based on the
 following paper: D.J. Best and N.I. Fisher, “Efficient simulation of the
 von Mises distribution.” Applied Statistics (1979): 152-157.</p>
@@ -8150,7 +8150,7 @@ <h2><span class="hidden-section">VonMises</span><a class="headerlink" href="#von
 <h2><span class="hidden-section">Weibull</span><a class="headerlink" href="#weibull" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.weibull.Weibull">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.weibull.</span></span><span class="sig-name descname"><span class="pre">Weibull</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/weibull.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.weibull.Weibull" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.weibull.</span></span><span class="sig-name descname"><span class="pre">Weibull</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concentration</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/weibull.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.weibull.Weibull" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.transformed_distribution.TransformedDistribution" title="torch.distributions.transformed_distribution.TransformedDistribution"><code class="xref py py-class docutils literal notranslate"><span class="pre">TransformedDistribution</span></code></a></p>
 <p>Samples from a two-parameter Weibull distribution.</p>
 <p class="rubric">Example</p>
@@ -8175,12 +8175,12 @@ <h2><span class="hidden-section">Weibull</span><a class="headerlink" href="#weib
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.weibull.Weibull.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/weibull.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.weibull.Weibull.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/weibull.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.weibull.Weibull.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.weibull.Weibull.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/weibull.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.weibull.Weibull.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/weibull.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.weibull.Weibull.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -8210,7 +8210,7 @@ <h2><span class="hidden-section">Weibull</span><a class="headerlink" href="#weib
 <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wishart" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.wishart.Wishart">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.wishart.</span></span><span class="sig-name descname"><span class="pre">Wishart</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">covariance_matrix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">precision_matrix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_tril</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/wishart.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.wishart.</span></span><span class="sig-name descname"><span class="pre">Wishart</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">covariance_matrix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">precision_matrix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_tril</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">validate_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/wishart.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart" title="Permalink to this definition">#</a></dt>
 <dd><p>Bases: <a class="reference internal" href="#torch.distributions.exp_family.ExponentialFamily" title="torch.distributions.exp_family.ExponentialFamily"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExponentialFamily</span></code></a></p>
 <p>Creates a Wishart distribution parameterized by a symmetric positive definite matrix <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="normal">Σ</mi></mrow><annotation encoding="application/x-tex">\Sigma</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord">Σ</span></span></span></span></span>,
 or its Cholesky decomposition <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="bold">Σ</mi><mo>=</mo><mi mathvariant="bold">L</mi><msup><mi mathvariant="bold">L</mi><mi mathvariant="normal">⊤</mi></msup></mrow><annotation encoding="application/x-tex">\mathbf{\Sigma} = \mathbf{L}\mathbf{L}^\top</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6861em;"></span><span class="mord mathbf">Σ</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.8491em;"></span><span class="mord mathbf">L</span><span class="mord"><span class="mord mathbf">L</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8491em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">⊤</span></span></span></span></span></span></span></span></span></span></span></span></p>
@@ -8258,12 +8258,12 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.wishart.Wishart.entropy">
-<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/wishart.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart.entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">entropy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/wishart.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart.entropy" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.wishart.Wishart.expand">
-<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/wishart.py#L152"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart.expand" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_instance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/wishart.py#L152"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart.expand" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -8273,7 +8273,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.wishart.Wishart.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/wishart.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/wishart.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart.log_prob" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -8293,7 +8293,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.wishart.Wishart.rsample">
-<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_try_correction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/wishart.py#L243"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart.rsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sample_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.Size([])</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_try_correction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/wishart.py#L243"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.wishart.Wishart.rsample" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>In some cases, sampling algorithm based on Bartlett decomposition may return singular matrix samples.
@@ -8331,7 +8331,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 <span id="kl-divergence"></span><h2><code class="docutils literal notranslate"><span class="pre">KL</span> <span class="pre">Divergence</span></code><a class="headerlink" href="#module-torch.distributions.kl" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributions.kl.kl_divergence">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.kl.</span></span><span class="sig-name descname"><span class="pre">kl_divergence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/kl.py#L164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kl.kl_divergence" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.kl.</span></span><span class="sig-name descname"><span class="pre">kl_divergence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/kl.py#L164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kl.kl_divergence" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute Kullback-Leibler divergence <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>K</mi><mi>L</mi><mo stretchy="false">(</mo><mi>p</mi><mi mathvariant="normal">∥</mi><mi>q</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">KL(p \| q)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">K</span><span class="mord mathnormal">L</span><span class="mopen">(</span><span class="mord mathnormal">p</span><span class="mord">∥</span><span class="mord mathnormal" style="margin-right:0.03588em;">q</span><span class="mclose">)</span></span></span></span></span> between two distributions.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mi>K</mi><mi>L</mi><mo stretchy="false">(</mo><mi>p</mi><mi mathvariant="normal">∥</mi><mi>q</mi><mo stretchy="false">)</mo><mo>=</mo><mo>∫</mo><mi>p</mi><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mi>log</mi><mo>⁡</mo><mfrac><mrow><mi>p</mi><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><mrow><mi>q</mi><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow></mfrac><mtext> </mtext><mi>d</mi><mi>x</mi></mrow><annotation encoding="application/x-tex">KL(p \| q) = \int p(x) \log\frac {p(x)} {q(x)} \,dx</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">K</span><span class="mord mathnormal">L</span><span class="mopen">(</span><span class="mord mathnormal">p</span><span class="mord">∥</span><span class="mord mathnormal" style="margin-right:0.03588em;">q</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:2.363em;vertical-align:-0.936em;"></span><span class="mop op-symbol large-op" style="margin-right:0.44445em;position:relative;top:-0.0011em;">∫</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">p</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mop">lo<span style="margin-right:0.01389em;">g</span></span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.427em;"><span style="top:-2.314em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">q</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord mathnormal">p</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.936em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">d</span><span class="mord mathnormal">x</span></span></span></span></span></div><dl class="field-list simple">
@@ -8448,7 +8448,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributions.kl.register_kl">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.kl.</span></span><span class="sig-name descname"><span class="pre">register_kl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">type_p</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_q</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/kl.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kl.register_kl" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.kl.</span></span><span class="sig-name descname"><span class="pre">register_kl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">type_p</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_q</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/kl.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.kl.register_kl" title="Permalink to this definition">#</a></dt>
 <dd><p>Decorator to register a pairwise function with <a class="reference internal" href="#torch.distributions.kl.kl_divergence" title="torch.distributions.kl.kl_divergence"><code class="xref py py-meth docutils literal notranslate"><span class="pre">kl_divergence()</span></code></a>.
 Usage:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nd">@register_kl</span><span class="p">(</span><span class="n">Normal</span><span class="p">,</span> <span class="n">Normal</span><span class="p">)</span>
@@ -8484,7 +8484,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 <span id="transforms"></span><h2><code class="docutils literal notranslate"><span class="pre">Transforms</span></code><a class="headerlink" href="#module-torch.distributions.transforms" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.AbsTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">AbsTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L720"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.AbsTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">AbsTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L720"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.AbsTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform via the mapping <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mi mathvariant="normal">∣</mi><mi>x</mi><mi mathvariant="normal">∣</mi></mrow><annotation encoding="application/x-tex">y = |x|</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord">∣</span><span class="mord mathnormal">x</span><span class="mord">∣</span></span></span></span></span>.</p>
 <dl class="field-list simple">
 </dl>
@@ -8492,7 +8492,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.AffineTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">AffineTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.AffineTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">AffineTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loc</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.AffineTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform via the pointwise affine mapping <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mtext>loc</mtext><mo>+</mo><mtext>scale</mtext><mo>×</mo><mi>x</mi></mrow><annotation encoding="application/x-tex">y = \text{loc} + \text{scale} \times x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord text"><span class="mord">loc</span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord text"><span class="mord">scale</span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -8509,7 +8509,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.CatTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">CatTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tseq</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L1058"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.CatTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">CatTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tseq</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L1058"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.CatTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform functor that applies a sequence of transforms <cite>tseq</cite>
 component-wise to each submatrix at <cite>dim</cite>, of length <cite>lengths[dim]</cite>,
 in a way compatible with <a class="reference internal" href="generated/torch.cat.html#torch.cat" title="torch.cat"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.cat()</span></code></a>.</p>
@@ -8527,7 +8527,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.ComposeTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">ComposeTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L280"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.ComposeTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">ComposeTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L280"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.ComposeTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Composes multiple transforms in a chain.
 The transforms being composed are responsible for caching.</p>
 <dl class="field-list simple">
@@ -8543,7 +8543,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.CorrCholeskyTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">CorrCholeskyTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L841"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.CorrCholeskyTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">CorrCholeskyTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L841"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.CorrCholeskyTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transforms an unconstrained real vector <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> with length <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>D</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>D</mi><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mi mathvariant="normal">/</mi><mn>2</mn></mrow><annotation encoding="application/x-tex">D*(D-1)/2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">∗</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">−</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord">1</span><span class="mclose">)</span><span class="mord">/2</span></span></span></span></span> into the
 Cholesky factor of a D-dimension correlation matrix. This Cholesky factor is a lower
 triangular matrix with positive diagonals and unit Euclidean norm for each row.
@@ -8577,7 +8577,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.CumulativeDistributionTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">CumulativeDistributionTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.CumulativeDistributionTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">CumulativeDistributionTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">distribution</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.CumulativeDistributionTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform via the cumulative distribution function of a probability distribution.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -8599,7 +8599,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.ExpTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">ExpTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L555"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.ExpTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">ExpTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L555"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.ExpTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform via the mapping <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">y = \exp(x)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">exp</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span></span>.</p>
 <dl class="field-list simple">
 </dl>
@@ -8607,7 +8607,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.IndependentTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">IndependentTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_transform</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reinterpreted_batch_ndims</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.IndependentTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">IndependentTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_transform</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reinterpreted_batch_ndims</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.IndependentTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around another transform to treat
 <code class="docutils literal notranslate"><span class="pre">reinterpreted_batch_ndims</span></code>-many extra of the right most dimensions as
 dependent. This has no effect on the forward or backward transforms, but
@@ -8626,7 +8626,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.LowerCholeskyTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">LowerCholeskyTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L1016"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.LowerCholeskyTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">LowerCholeskyTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L1016"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.LowerCholeskyTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform from unconstrained matrices to lower-triangular matrices with
 nonnegative diagonal entries.</p>
 <p>This is useful for parameterizing positive definite matrices in terms of
@@ -8637,7 +8637,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.PositiveDefiniteTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">PositiveDefiniteTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L1038"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.PositiveDefiniteTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">PositiveDefiniteTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L1038"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.PositiveDefiniteTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform from unconstrained matrices to positive-definite matrices.</p>
 <dl class="field-list simple">
 </dl>
@@ -8645,7 +8645,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.PowerTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">PowerTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">exponent</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.PowerTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">PowerTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">exponent</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.PowerTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform via the mapping <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><msup><mi>x</mi><mtext>exponent</mtext></msup></mrow><annotation encoding="application/x-tex">y = x^{\text{exponent}}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.7936em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.7936em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">exponent</span></span></span></span></span></span></span></span></span></span></span></span></span></span>.</p>
 <dl class="field-list simple">
 </dl>
@@ -8653,7 +8653,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.ReshapeTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">ReshapeTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L481"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.ReshapeTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">ReshapeTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L481"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.ReshapeTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Unit Jacobian transform to reshape the rightmost part of a tensor.</p>
 <p>Note that <code class="docutils literal notranslate"><span class="pre">in_shape</span></code> and <code class="docutils literal notranslate"><span class="pre">out_shape</span></code> must have the same number of
 elements, just as for <a class="reference internal" href="generated/torch.Tensor.reshape.html#torch.Tensor.reshape" title="torch.Tensor.reshape"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.Tensor.reshape()</span></code></a>.</p>
@@ -8671,7 +8671,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.SigmoidTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">SigmoidTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L626"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.SigmoidTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">SigmoidTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L626"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.SigmoidTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform via the mapping <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mfrac><mn>1</mn><mrow><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow></mfrac></mrow><annotation encoding="application/x-tex">y = \frac{1}{1 + \exp(-x)}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.3651em;vertical-align:-0.52em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8451em;"><span style="top:-2.655em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">1</span><span class="mbin mtight">+</span><span class="mop mtight"><span class="mtight">e</span><span class="mtight">x</span><span class="mtight">p</span></span><span class="mopen mtight">(</span><span class="mord mtight">−</span><span class="mord mathnormal mtight">x</span><span class="mclose mtight">)</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.394em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">1</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.52em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span></span></span></span></span> and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mo>=</mo><mtext>logit</mtext><mo stretchy="false">(</mo><mi>y</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">x = \text{logit}(y)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">logit</span></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mclose">)</span></span></span></span></span>.</p>
 <dl class="field-list simple">
 </dl>
@@ -8679,7 +8679,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.SoftplusTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">SoftplusTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L651"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.SoftplusTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">SoftplusTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L651"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.SoftplusTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform via the mapping <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>Softplus</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>log</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{Softplus}(x) = \log(1 + \exp(x))</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">Softplus</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">lo<span style="margin-right:0.01389em;">g</span></span><span class="mopen">(</span><span class="mord">1</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">exp</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">))</span></span></span></span></span>.
 The implementation reverts to the linear function when <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mo>&gt;</mo><mn>20</mn></mrow><annotation encoding="application/x-tex">x &gt; 20</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5782em;vertical-align:-0.0391em;"></span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">&gt;</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord">20</span></span></span></span></span>.</p>
 <dl class="field-list simple">
@@ -8688,7 +8688,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.TanhTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">TanhTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.TanhTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">TanhTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.TanhTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform via the mapping <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">y = \tanh(x)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">tanh</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span></span>.</p>
 <p>It is equivalent to</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">ComposeTransform</span><span class="p">(</span>
@@ -8709,7 +8709,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.SoftmaxTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">SoftmaxTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L924"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.SoftmaxTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">SoftmaxTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L924"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.SoftmaxTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform from unconstrained space to the simplex via <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">y = \exp(x)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">exp</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span></span> then
 normalizing.</p>
 <p>This is not bijective and cannot be used for HMC. However this acts mostly
@@ -8721,7 +8721,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.StackTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">StackTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tseq</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L1170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.StackTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">StackTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tseq</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L1170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.StackTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform functor that applies a sequence of transforms <cite>tseq</cite>
 component-wise to each submatrix at <cite>dim</cite>
 in a way compatible with <a class="reference internal" href="generated/torch.stack.html#torch.stack" title="torch.stack"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.stack()</span></code></a>.</p>
@@ -8737,7 +8737,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.StickBreakingTransform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">StickBreakingTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L960"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.StickBreakingTransform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">StickBreakingTransform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L960"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.StickBreakingTransform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform from unconstrained space to the simplex of one additional
 dimension via a stick-breaking process.</p>
 <p>This transform arises as an iterated sigmoid transform in a stick-breaking
@@ -8752,7 +8752,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.transforms.Transform">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">Transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.Transform" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.transforms.</span></span><span class="sig-name descname"><span class="pre">Transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cache_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.Transform" title="Permalink to this definition">#</a></dt>
 <dd><p>Abstract class for invertable transformations with computable log
 det jacobians. They are primarily used in
 <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.distributions.TransformedDistribution</span></code>.</p>
@@ -8811,20 +8811,20 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transforms.Transform.log_abs_det_jacobian">
-<span class="sig-name descname"><span class="pre">log_abs_det_jacobian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.Transform.log_abs_det_jacobian" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_abs_det_jacobian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.Transform.log_abs_det_jacobian" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the log det jacobian <cite>log |dy/dx|</cite> given input and output.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transforms.Transform.forward_shape">
-<span class="sig-name descname"><span class="pre">forward_shape</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.Transform.forward_shape" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward_shape</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.Transform.forward_shape" title="Permalink to this definition">#</a></dt>
 <dd><p>Infers the shape of the forward computation, given the input shape.
 Defaults to preserving shape.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.transforms.Transform.inverse_shape">
-<span class="sig-name descname"><span class="pre">inverse_shape</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/transforms.py#L210"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.Transform.inverse_shape" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">inverse_shape</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/transforms.py#L210"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.transforms.Transform.inverse_shape" title="Permalink to this definition">#</a></dt>
 <dd><p>Infers the shapes of the inverse computation, given the output shape.
 Defaults to preserving shape.</p>
 </dd></dl>
@@ -8836,7 +8836,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 <span id="constraints"></span><h2><code class="docutils literal notranslate"><span class="pre">Constraints</span></code><a class="headerlink" href="#module-torch.distributions.constraints" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.constraints.Constraint">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">Constraint</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.Constraint" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">Constraint</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.Constraint" title="Permalink to this definition">#</a></dt>
 <dd><p>Abstract base class for constraints.</p>
 <p>A constraint object represents a region over which a variable is valid,
 e.g. within which a variable can be optimized.</p>
@@ -8853,7 +8853,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.constraints.Constraint.check">
-<span class="sig-name descname"><span class="pre">check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.Constraint.check" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.Constraint.check" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a byte tensor of <code class="docutils literal notranslate"><span class="pre">sample_shape</span> <span class="pre">+</span> <span class="pre">batch_shape</span></code> indicating
 whether each event in value satisfies this constraint.</p>
 </dd></dl>
@@ -8862,55 +8862,55 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.cat">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">cat</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L640"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.cat" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">cat</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L640"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.cat" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_Cat</span></code></p>
 </dd></dl>
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.dependent_property">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">dependent_property</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.dependent_property" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">dependent_property</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.dependent_property" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_DependentProperty</span></code></p>
 </dd></dl>
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.greater_than">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">greater_than</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L415"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.greater_than" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">greater_than</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L415"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.greater_than" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_GreaterThan</span></code></p>
 </dd></dl>
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.greater_than_eq">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">greater_than_eq</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L433"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.greater_than_eq" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">greater_than_eq</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L433"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.greater_than_eq" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_GreaterThanEq</span></code></p>
 </dd></dl>
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.independent">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">independent</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L230"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.independent" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">independent</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L230"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.independent" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_IndependentConstraint</span></code></p>
 </dd></dl>
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.integer_interval">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">integer_interval</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L341"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.integer_interval" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">integer_interval</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L341"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.integer_interval" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_IntegerInterval</span></code></p>
 </dd></dl>
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.interval">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">interval</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L469"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.interval" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">interval</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L469"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.interval" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_Interval</span></code></p>
 </dd></dl>
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.half_open_interval">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">half_open_interval</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L490"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.half_open_interval" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">half_open_interval</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L490"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.half_open_interval" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_HalfOpenInterval</span></code></p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributions.constraints.is_dependent">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">is_dependent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">constraint</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.is_dependent" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">is_dependent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">constraint</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.is_dependent" title="Permalink to this definition">#</a></dt>
 <dd><p>Checks if <code class="docutils literal notranslate"><span class="pre">constraint</span></code> is a <code class="docutils literal notranslate"><span class="pre">_Dependent</span></code> object.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -8943,13 +8943,13 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.less_than">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">less_than</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L451"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.less_than" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">less_than</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L451"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.less_than" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_LessThan</span></code></p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.constraints.MixtureSameFamilyConstraint">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">MixtureSameFamilyConstraint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_constraint</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.MixtureSameFamilyConstraint" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">MixtureSameFamilyConstraint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_constraint</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.MixtureSameFamilyConstraint" title="Permalink to this definition">#</a></dt>
 <dd><p>Constraint for the <code class="xref py py-class docutils literal notranslate"><span class="pre">MixtureSameFamily</span></code>
 distribution that adds back the rightmost batch dimension before
 performing the validity check with the component distribution
@@ -8963,7 +8963,7 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.constraints.MixtureSameFamilyConstraint.check">
-<span class="sig-name descname"><span class="pre">check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L296"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.MixtureSameFamilyConstraint.check" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L296"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.MixtureSameFamilyConstraint.check" title="Permalink to this definition">#</a></dt>
 <dd><p>Check validity of <code class="docutils literal notranslate"><span class="pre">value</span></code> as a possible outcome of sampling
 the <code class="xref py py-class docutils literal notranslate"><span class="pre">MixtureSameFamily</span></code> distribution.</p>
 </dd></dl>
@@ -8972,13 +8972,13 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.multinomial">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">multinomial</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L523"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.multinomial" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">multinomial</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L523"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.multinomial" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_Multinomial</span></code></p>
 </dd></dl>
 
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.distributions.constraints.stack">
-<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">stack</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraints.py#L676"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.stack" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributions.constraints.</span></span><span class="sig-name descname"><span class="pre">stack</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraints.py#L676"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraints.stack" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <code class="xref py py-class docutils literal notranslate"><span class="pre">_Stack</span></code></p>
 </dd></dl>
 
@@ -9051,11 +9051,11 @@ <h2><span class="hidden-section">Wishart</span><a class="headerlink" href="#wish
 object.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributions.constraint_registry.ConstraintRegistry">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.constraint_registry.</span></span><span class="sig-name descname"><span class="pre">ConstraintRegistry</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraint_registry.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraint_registry.ConstraintRegistry" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributions.constraint_registry.</span></span><span class="sig-name descname"><span class="pre">ConstraintRegistry</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraint_registry.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraint_registry.ConstraintRegistry" title="Permalink to this definition">#</a></dt>
 <dd><p>Registry to link constraints to transforms.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributions.constraint_registry.ConstraintRegistry.register">
-<span class="sig-name descname"><span class="pre">register</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">constraint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributions/constraint_registry.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraint_registry.ConstraintRegistry.register" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">constraint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributions/constraint_registry.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributions.constraint_registry.ConstraintRegistry.register" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a <a class="reference internal" href="#torch.distributions.constraints.Constraint" title="torch.distributions.constraints.Constraint"><code class="xref py py-class docutils literal notranslate"><span class="pre">Constraint</span></code></a>
 subclass in this registry. Usage:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nd">@my_registry</span><span class="o">.</span><span class="n">register</span><span class="p">(</span><span class="n">MyConstraintClass</span><span class="p">)</span>
diff --git a/2.9/dlpack.html b/2.9/dlpack.html
index 87f4391352e..37bac8eed1f 100644
--- a/2.9/dlpack.html
+++ b/2.9/dlpack.html
@@ -4396,7 +4396,7 @@ <h1>torch.utils.dlpack<a class="headerlink" href="#torch-utils-dlpack" title="Pe
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Jul 11, 2018 | Last Updated On: Jun 13, 2025</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.dlpack.from_dlpack">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.dlpack.</span></span><span class="sig-name descname"><span class="pre">from_dlpack</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ext_tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/dlpack.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.dlpack.from_dlpack" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.dlpack.</span></span><span class="sig-name descname"><span class="pre">from_dlpack</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ext_tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/dlpack.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.dlpack.from_dlpack" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts a tensor from an external library into a <code class="docutils literal notranslate"><span class="pre">torch.Tensor</span></code>.</p>
 <p>The returned PyTorch tensor will share the memory with the input tensor
 (which may have come from another library). Note that in-place operations
diff --git a/2.9/elastic/agent.html b/2.9/elastic/agent.html
index 6251aea2128..24ff4ba44f1 100644
--- a/2.9/elastic/agent.html
+++ b/2.9/elastic/agent.html
@@ -4431,7 +4431,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 are relevant to understanding the role of the <code class="docutils literal notranslate"><span class="pre">agent</span></code> in torchelastic.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.ElasticAgent">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">ElasticAgent</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L375"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.ElasticAgent" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">ElasticAgent</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L375"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.ElasticAgent" title="Permalink to this definition">#</a></dt>
 <dd><p>An agent process responsible for managing one or more worker processes.</p>
 <p>The worker processes are assumed to be regular distributed PyTorch scripts.
 When the worker process is created by the agent, the agent provides the
@@ -4463,7 +4463,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.ElasticAgent.get_worker_group">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_worker_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">role</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'default'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L425"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.ElasticAgent.get_worker_group" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_worker_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">role</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'default'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L425"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.ElasticAgent.get_worker_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the <code class="docutils literal notranslate"><span class="pre">WorkerGroup</span></code> for the given <code class="docutils literal notranslate"><span class="pre">role</span></code>.</p>
 <p>Note that the worker group is a mutable object and hence in a
 multi-threaded/process environment it may change state.
@@ -4478,7 +4478,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.ElasticAgent.run">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">role</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'default'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.ElasticAgent.run" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">role</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'default'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.ElasticAgent.run" title="Permalink to this definition">#</a></dt>
 <dd><p>Run the agent.</p>
 <p>Supports retrying the worker group on failures up to <code class="docutils literal notranslate"><span class="pre">max_restarts</span></code>.</p>
 <dl class="field-list simple">
@@ -4499,7 +4499,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.WorkerSpec">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">WorkerSpec</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">role</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_world_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rdzv_handler</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_restarts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">monitor_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">master_port</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">master_addr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_addr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_log_handler</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'null'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerSpec" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">WorkerSpec</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">role</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_world_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rdzv_handler</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_restarts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">monitor_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">master_port</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">master_addr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_addr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_log_handler</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'null'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerSpec" title="Permalink to this definition">#</a></dt>
 <dd><p>Blueprint information about a particular type of worker.</p>
 <p>For a given role, there must only exist a single worker spec.
 Worker spec is expected to be homogeneous across all nodes (machine),
@@ -4532,7 +4532,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.WorkerSpec.get_entrypoint_name">
-<span class="sig-name descname"><span class="pre">get_entrypoint_name</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerSpec.get_entrypoint_name" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_entrypoint_name</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerSpec.get_entrypoint_name" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the entry point name.</p>
 <p>If the entrypoint is a function (e.g. <code class="docutils literal notranslate"><span class="pre">Callable</span></code>) returns its <code class="docutils literal notranslate"><span class="pre">__qualname__</span></code>
 else if the entrypoint is a binary (e.g. <code class="docutils literal notranslate"><span class="pre">str</span></code>), returns the binary name.</p>
@@ -4542,7 +4542,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.WorkerState">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">WorkerState</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerState" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">WorkerState</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerState" title="Permalink to this definition">#</a></dt>
 <dd><p>A state of the <code class="docutils literal notranslate"><span class="pre">WorkerGroup</span></code>.</p>
 <p>Workers in a worker group change state as a unit. If a single worker
 in a worker group fails the entire set is considered failed:</p>
@@ -4574,7 +4574,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 self terminating and allowing the job manager to retry the node.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.WorkerState.is_running">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">is_running</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerState.is_running" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">is_running</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerState.is_running" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the Worker.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4591,7 +4591,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.Worker">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">Worker</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">local_rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">role_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">role_world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.Worker" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">Worker</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">local_rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">role_rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">role_world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.Worker" title="Permalink to this definition">#</a></dt>
 <dd><p>A worker instance.</p>
 <p>Contrast this with <code class="docutils literal notranslate"><span class="pre">WorkerSpec</span></code> that represents the specifications of a
 worker. A <code class="docutils literal notranslate"><span class="pre">Worker</span></code> is created from a <code class="docutils literal notranslate"><span class="pre">WorkerSpec</span></code>. A <code class="docutils literal notranslate"><span class="pre">Worker</span></code> is to
@@ -4616,7 +4616,7 @@ <h2>Concepts<a class="headerlink" href="#concepts" title="Permalink to this head
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.WorkerGroup">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">WorkerGroup</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">spec</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L248"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerGroup" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">WorkerGroup</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">spec</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L248"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.WorkerGroup" title="Permalink to this definition">#</a></dt>
 <dd><p>A set of <code class="docutils literal notranslate"><span class="pre">Worker</span></code> instances.</p>
 <p>The class defines a set of <code class="docutils literal notranslate"><span class="pre">Worker</span></code> instances for the given <code class="docutils literal notranslate"><span class="pre">WorkerSpec</span></code> managed by <code class="docutils literal notranslate"><span class="pre">ElasticAgent</span></code>. Whether the worker
 group contains cross instance workers or not depends on the implementation of the agent.</p>
@@ -4630,7 +4630,7 @@ <h2>Implementations<a class="headerlink" href="#implementations" title="Permalin
 <p>Below are the agent implementations provided by torchelastic.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.local_elastic_agent.LocalElasticAgent">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.local_elastic_agent.</span></span><span class="sig-name descname"><span class="pre">LocalElasticAgent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'spawn'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exit_barrier_timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">300</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefix_template</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/local_elastic_agent.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.local_elastic_agent.LocalElasticAgent" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.local_elastic_agent.</span></span><span class="sig-name descname"><span class="pre">LocalElasticAgent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'spawn'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exit_barrier_timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">300</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefix_template</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/local_elastic_agent.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.local_elastic_agent.LocalElasticAgent" title="Permalink to this definition">#</a></dt>
 <dd><p>An implementation of <code class="xref py py-class docutils literal notranslate"><span class="pre">torchelastic.agent.server.ElasticAgent</span></code> that handles host-local workers.</p>
 <p>This agent is deployed per host and is configured to spawn <code class="docutils literal notranslate"><span class="pre">n</span></code> workers.
 When using GPUs, <code class="docutils literal notranslate"><span class="pre">n</span></code> maps to the number of GPUs available on the host.</p>
@@ -4716,7 +4716,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 to implement.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">SimpleElasticAgent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exit_barrier_timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">300</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.</span></span><span class="sig-name descname"><span class="pre">SimpleElasticAgent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exit_barrier_timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">300</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent" title="Permalink to this definition">#</a></dt>
 <dd><p>An <code class="docutils literal notranslate"><span class="pre">ElasticAgent</span></code> that manages one particular type of worker role.</p>
 <p>An <code class="docutils literal notranslate"><span class="pre">ElasticAgent</span></code> that manages workers (<code class="docutils literal notranslate"><span class="pre">WorkerGroup</span></code>) for a single <code class="docutils literal notranslate"><span class="pre">WorkerSpec</span></code>
 such as one particular type of worker role.</p>
@@ -4724,7 +4724,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._assign_worker_ranks">
-<span class="sig-name descname"><span class="pre">_assign_worker_ranks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_world_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">spec</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L556"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._assign_worker_ranks" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">_assign_worker_ranks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_world_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">spec</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L556"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._assign_worker_ranks" title="Permalink to this definition">#</a></dt>
 <dd><p>Determine proper ranks for worker processes.</p>
 <p>Fast Path: when all workers have the same role and world size. We calculate
 the global rank to be group_rank * group_world_size + local_rank. And the
@@ -4760,7 +4760,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._exit_barrier">
-<span class="sig-name descname"><span class="pre">_exit_barrier</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L934"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._exit_barrier" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">_exit_barrier</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L934"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._exit_barrier" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a barrier that keeps the agent process alive until all workers finish.</p>
 <p>Wait for <code class="docutils literal notranslate"><span class="pre">exit_barrier_timeout</span></code> seconds for all agents to finish
 executing their local workers (either successfully or not). This
@@ -4770,7 +4770,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._initialize_workers">
-<span class="sig-name descname"><span class="pre">_initialize_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._initialize_workers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">_initialize_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._initialize_workers" title="Permalink to this definition">#</a></dt>
 <dd><p>Start a fresh set of workers for the worker_group.</p>
 <p>Essentially, a rendezvous followed by a <code class="docutils literal notranslate"><span class="pre">start_workers</span></code>.
 The caller should first call <code class="docutils literal notranslate"><span class="pre">_stop_workers()</span></code> to stop running workers
@@ -4784,7 +4784,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._monitor_workers">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">_monitor_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._monitor_workers" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">_monitor_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._monitor_workers" title="Permalink to this definition">#</a></dt>
 <dd><p>Check on the workers for the <code class="docutils literal notranslate"><span class="pre">worker_group</span></code>.</p>
 <p>This function also returns the new state of the worker group.</p>
 <dl class="field-list simple">
@@ -4796,7 +4796,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._rendezvous">
-<span class="sig-name descname"><span class="pre">_rendezvous</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L490"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._rendezvous" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">_rendezvous</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L490"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._rendezvous" title="Permalink to this definition">#</a></dt>
 <dd><p>Run rendezvous for the workers specified by the worker spec.</p>
 <p>Assigns workers a new global rank and world size.
 Updates the rendezvous store for the worker group.</p>
@@ -4806,7 +4806,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._restart_workers">
-<span class="sig-name descname"><span class="pre">_restart_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L701"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._restart_workers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">_restart_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L701"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._restart_workers" title="Permalink to this definition">#</a></dt>
 <dd><p>Restart (stops, rendezvous, starts) all local workers in the group.</p>
 <dl class="field-list simple">
 </dl>
@@ -4814,7 +4814,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._shutdown">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">_shutdown</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">death_sig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Signals.SIGTERM</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L481"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._shutdown" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">_shutdown</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">death_sig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Signals.SIGTERM</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L481"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._shutdown" title="Permalink to this definition">#</a></dt>
 <dd><p>Clean up any resources that were allocated during the agent’s work.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4825,7 +4825,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._start_workers">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">_start_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._start_workers" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">_start_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._start_workers" title="Permalink to this definition">#</a></dt>
 <dd><p>Start <code class="docutils literal notranslate"><span class="pre">worker_group.spec.local_world_size</span></code> number of workers.</p>
 <p>This is according to worker spec for the worker group .
 Returns a map of <code class="docutils literal notranslate"><span class="pre">local_rank</span></code> to worker <code class="docutils literal notranslate"><span class="pre">id</span></code>.</p>
@@ -4838,7 +4838,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.SimpleElasticAgent._stop_workers">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">_stop_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L463"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._stop_workers" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">_stop_workers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L463"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.SimpleElasticAgent._stop_workers" title="Permalink to this definition">#</a></dt>
 <dd><p>Stop all workers in the given worker group.</p>
 <p>Implementers must deal with workers in all states defined by
 <code class="docutils literal notranslate"><span class="pre">WorkerState</span></code>. That is, it must gracefully handle stopping
@@ -4851,7 +4851,7 @@ <h2>Extending the Agent<a class="headerlink" href="#extending-the-agent" title="
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.api.RunResult">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.api.</span></span><span class="sig-name descname"><span class="pre">RunResult</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_values=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">failures=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/api.py#L337"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.api.RunResult" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.api.</span></span><span class="sig-name descname"><span class="pre">RunResult</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_values=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">failures=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/api.py#L337"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.api.RunResult" title="Permalink to this definition">#</a></dt>
 <dd><p>Return results of the worker executions.</p>
 <p>Run results follow an “all-or-nothing” policy where the run is successful if and
 only if ALL local workers managed by this agent complete successfully.</p>
@@ -4900,7 +4900,7 @@ <h2>Health Check Server<a class="headerlink" href="#health-check-server" title="
 Additionally, health check server will have callback to check watchdog is alive.</p>
 <span class="target" id="module-torch.distributed.elastic.agent.server.health_check_server"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.health_check_server.</span></span><span class="sig-name descname"><span class="pre">HealthCheckServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alive_callback</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/health_check_server.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.health_check_server.</span></span><span class="sig-name descname"><span class="pre">HealthCheckServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alive_callback</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/health_check_server.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer" title="Permalink to this definition">#</a></dt>
 <dd><p>Interface for health check monitoring server, which can be extended
 by starting tcp/http server on the specified port.</p>
 <dl class="field-list simple">
@@ -4914,7 +4914,7 @@ <h2>Health Check Server<a class="headerlink" href="#health-check-server" title="
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer.start">
-<span class="sig-name descname"><span class="pre">start</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/health_check_server.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer.start" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">start</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/health_check_server.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer.start" title="Permalink to this definition">#</a></dt>
 <dd><p>Unsupported functionality for Pytorch, doesn’t start any health check server</p>
 <dl class="field-list simple">
 </dl>
@@ -4922,7 +4922,7 @@ <h2>Health Check Server<a class="headerlink" href="#health-check-server" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer.stop">
-<span class="sig-name descname"><span class="pre">stop</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/health_check_server.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer.stop" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">stop</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/health_check_server.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.health_check_server.HealthCheckServer.stop" title="Permalink to this definition">#</a></dt>
 <dd><p>Function to stop health check server</p>
 <dl class="field-list simple">
 </dl>
@@ -4932,7 +4932,7 @@ <h2>Health Check Server<a class="headerlink" href="#health-check-server" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.agent.server.health_check_server.create_healthcheck_server">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.health_check_server.</span></span><span class="sig-name descname"><span class="pre">create_healthcheck_server</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alive_callback</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/agent/server/health_check_server.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.health_check_server.create_healthcheck_server" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.agent.server.health_check_server.</span></span><span class="sig-name descname"><span class="pre">create_healthcheck_server</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alive_callback</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/agent/server/health_check_server.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.agent.server.health_check_server.create_healthcheck_server" title="Permalink to this definition">#</a></dt>
 <dd><p>creates health check server object</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/elastic/control_plane.html b/2.9/elastic/control_plane.html
index 0b59593aced..78a9015f867 100644
--- a/2.9/elastic/control_plane.html
+++ b/2.9/elastic/control_plane.html
@@ -4407,7 +4407,7 @@
 into your application.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.control_plane.worker_main">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.control_plane.</span></span><span class="sig-name descname"><span class="pre">worker_main</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/control_plane.py#L26"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.control_plane.worker_main" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.control_plane.</span></span><span class="sig-name descname"><span class="pre">worker_main</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/control_plane.py#L26"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.control_plane.worker_main" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a context manager that wraps your main entry function. This combines
 the existing <code class="docutils literal notranslate"><span class="pre">errors.record</span></code> logic as well as a new <code class="docutils literal notranslate"><span class="pre">_WorkerServer</span></code> that
 exposes handlers via a unix socket specified by
diff --git a/2.9/elastic/errors.html b/2.9/elastic/errors.html
index 38b51cbd661..930853c8c55 100644
--- a/2.9/elastic/errors.html
+++ b/2.9/elastic/errors.html
@@ -4460,7 +4460,7 @@
 <h2>Methods and Classes<a class="headerlink" href="#methods-and-classes" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.errors.record">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.errors.</span></span><span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_handler</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/errors/__init__.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.errors.record" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.errors.</span></span><span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_handler</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/errors/__init__.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.errors.record" title="Permalink to this definition">#</a></dt>
 <dd><p>Syntactic sugar to record errors/exceptions that happened in the decorated
 function using the provided <code class="docutils literal notranslate"><span class="pre">error_handler</span></code>.</p>
 <p>Using this decorator is equivalent to:</p>
@@ -4501,7 +4501,7 @@ <h2>Methods and Classes<a class="headerlink" href="#methods-and-classes" title="
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.errors.ChildFailedError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.errors.</span></span><span class="sig-name descname"><span class="pre">ChildFailedError</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">failures</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/errors/__init__.py#L200"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.errors.ChildFailedError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.errors.</span></span><span class="sig-name descname"><span class="pre">ChildFailedError</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">failures</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/errors/__init__.py#L200"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.errors.ChildFailedError" title="Permalink to this definition">#</a></dt>
 <dd><p>Special exception type that can be raised from a function annotated with the
 <code class="docutils literal notranslate"><span class="pre">&#64;record</span></code> decorator to have the child process’ (root exception) propagate
 up the stack as-is (e.g. without being wrapped in the parent’s traceback).</p>
@@ -4538,7 +4538,7 @@ <h2>Methods and Classes<a class="headerlink" href="#methods-and-classes" title="
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.errors.ErrorHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.errors.</span></span><span class="sig-name descname"><span class="pre">ErrorHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/errors/error_handler.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.errors.ErrorHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.errors.</span></span><span class="sig-name descname"><span class="pre">ErrorHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/errors/error_handler.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.errors.ErrorHandler" title="Permalink to this definition">#</a></dt>
 <dd><p>Write the provided exception object along with some other metadata about
 the error in a structured way in JSON format to an error file specified by the
 environment variable: <code class="docutils literal notranslate"><span class="pre">TORCHELASTIC_ERROR_FILE</span></code>. If this environment
@@ -4550,7 +4550,7 @@ <h2>Methods and Classes<a class="headerlink" href="#methods-and-classes" title="
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.errors.ProcessFailure">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.errors.</span></span><span class="sig-name descname"><span class="pre">ProcessFailure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">local_rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pid</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exitcode</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_file</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/errors/__init__.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.errors.ProcessFailure" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.errors.</span></span><span class="sig-name descname"><span class="pre">ProcessFailure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">local_rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pid</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exitcode</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_file</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/errors/__init__.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.errors.ProcessFailure" title="Permalink to this definition">#</a></dt>
 <dd><p>Represent the failed process result. When the worker process fails, it may record failure root cause into the file.</p>
 <p>Tries to read the failure timestamp from the provided <code class="docutils literal notranslate"><span class="pre">error_file</span></code>,
 if the <code class="docutils literal notranslate"><span class="pre">error_file</span></code> does not exist, the timestamp is the current
diff --git a/2.9/elastic/events.html b/2.9/elastic/events.html
index 115248aa1a3..2ee702e8f74 100644
--- a/2.9/elastic/events.html
+++ b/2.9/elastic/events.html
@@ -4417,14 +4417,14 @@
 <h2>API Methods<a class="headerlink" href="#api-methods" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.events.record">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.</span></span><span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'null'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/events/__init__.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.record" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.</span></span><span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'null'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/events/__init__.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.record" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.events.construct_and_record_rdzv_event">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.</span></span><span class="sig-name descname"><span class="pre">construct_and_record_rdzv_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">message</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">node_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hostname</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pid</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">master_endpoint</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/events/__init__.py#L83"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.construct_and_record_rdzv_event" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.</span></span><span class="sig-name descname"><span class="pre">construct_and_record_rdzv_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">message</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">node_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hostname</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pid</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">master_endpoint</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/events/__init__.py#L83"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.construct_and_record_rdzv_event" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize rendezvous event object and record its operations.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4471,7 +4471,7 @@ <h2>API Methods<a class="headerlink" href="#api-methods" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.events.get_logging_handler">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.</span></span><span class="sig-name descname"><span class="pre">get_logging_handler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'null'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/events/handlers.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.get_logging_handler" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.</span></span><span class="sig-name descname"><span class="pre">get_logging_handler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'null'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/events/handlers.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.get_logging_handler" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/logging.html#logging.Handler" title="(in Python v3.14)"><em>Handler</em></a></p>
@@ -4484,7 +4484,7 @@ <h2>API Methods<a class="headerlink" href="#api-methods" title="Permalink to thi
 <h2>Event Objects<a class="headerlink" href="#event-objects" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.events.api.Event">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.api.</span></span><span class="sig-name descname"><span class="pre">Event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timestamp=0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/events/api.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.api.Event" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.api.</span></span><span class="sig-name descname"><span class="pre">Event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timestamp=0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/events/api.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.api.Event" title="Permalink to this definition">#</a></dt>
 <dd><p>The class represents the generic event that occurs during the torchelastic job execution.</p>
 <p>The event can be any kind of meaningful action.</p>
 <dl class="field-list simple">
@@ -4501,7 +4501,7 @@ <h2>Event Objects<a class="headerlink" href="#event-objects" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.events.api.EventSource">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.api.</span></span><span class="sig-name descname"><span class="pre">EventSource</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/events/api.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.api.EventSource" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.events.api.</span></span><span class="sig-name descname"><span class="pre">EventSource</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/events/api.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.events.api.EventSource" title="Permalink to this definition">#</a></dt>
 <dd><p>Known identifiers of the event producers.</p>
 </dd></dl>
 
diff --git a/2.9/elastic/metrics.html b/2.9/elastic/metrics.html
index 5a6ec2ed009..43e832b89f7 100644
--- a/2.9/elastic/metrics.html
+++ b/2.9/elastic/metrics.html
@@ -4518,17 +4518,17 @@ <h2>Metric Handlers<a class="headerlink" href="#metric-handlers" title="Permalin
 <p>Below are the metric handlers that come included with torchelastic.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.metrics.api.MetricHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.api.</span></span><span class="sig-name descname"><span class="pre">MetricHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/metrics/api.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.api.MetricHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.api.</span></span><span class="sig-name descname"><span class="pre">MetricHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/metrics/api.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.api.MetricHandler" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.metrics.api.ConsoleMetricHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.api.</span></span><span class="sig-name descname"><span class="pre">ConsoleMetricHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/metrics/api.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.api.ConsoleMetricHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.api.</span></span><span class="sig-name descname"><span class="pre">ConsoleMetricHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/metrics/api.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.api.ConsoleMetricHandler" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.metrics.api.NullMetricHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.api.</span></span><span class="sig-name descname"><span class="pre">NullMetricHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/metrics/api.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.api.NullMetricHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.api.</span></span><span class="sig-name descname"><span class="pre">NullMetricHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/metrics/api.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.api.NullMetricHandler" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
@@ -4536,14 +4536,14 @@ <h2>Metric Handlers<a class="headerlink" href="#metric-handlers" title="Permalin
 <h2>Methods<a class="headerlink" href="#methods" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.metrics.configure">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.</span></span><span class="sig-name descname"><span class="pre">configure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">handler</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/metrics/api.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.configure" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.</span></span><span class="sig-name descname"><span class="pre">configure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">handler</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/metrics/api.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.configure" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.metrics.prof">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.</span></span><span class="sig-name descname"><span class="pre">prof</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'torchelastic'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/metrics/api.py#L111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.prof" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.</span></span><span class="sig-name descname"><span class="pre">prof</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'torchelastic'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/metrics/api.py#L111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.prof" title="Permalink to this definition">#</a></dt>
 <dd><p>&#64;profile decorator publishes duration.ms, count, success, failure metrics for the function that it decorates.</p>
 <p>The metric name defaults to the qualified name (<code class="docutils literal notranslate"><span class="pre">class_name.def_name</span></code>) of the function.
 If the function does not belong to a class, it uses the leaf module name instead.</p>
@@ -4564,7 +4564,7 @@ <h2>Methods<a class="headerlink" href="#methods" title="Permalink to this headin
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.metrics.put_metric">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.</span></span><span class="sig-name descname"><span class="pre">put_metric</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metric_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metric_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metric_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'torchelastic'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/metrics/api.py#L191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.put_metric" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.metrics.</span></span><span class="sig-name descname"><span class="pre">put_metric</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metric_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metric_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metric_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'torchelastic'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/metrics/api.py#L191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.metrics.put_metric" title="Permalink to this definition">#</a></dt>
 <dd><p>Publish a metric data point.</p>
 <p>Usage</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">put_metric</span><span class="p">(</span><span class="s2">&quot;metric_name&quot;</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
diff --git a/2.9/elastic/multiprocessing.html b/2.9/elastic/multiprocessing.html
index 021b90bc342..a4fa37e223a 100644
--- a/2.9/elastic/multiprocessing.html
+++ b/2.9/elastic/multiprocessing.html
@@ -4454,7 +4454,7 @@
 <h2>Starting Multiple Workers<a class="headerlink" href="#starting-multiple-workers" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.start_processes">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">start_processes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">envs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'spawn'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/__init__.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.start_processes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">start_processes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">envs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'spawn'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/__init__.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.start_processes" title="Permalink to this definition">#</a></dt>
 <dd><p>Start <code class="docutils literal notranslate"><span class="pre">n</span></code> copies of <code class="docutils literal notranslate"><span class="pre">entrypoint</span></code> processes with the provided options.</p>
 <p><code class="docutils literal notranslate"><span class="pre">entrypoint</span></code> is either a <code class="docutils literal notranslate"><span class="pre">Callable</span></code> (function) or a <code class="docutils literal notranslate"><span class="pre">str</span></code> (binary).
 The number of copies is determined by the number of entries for <code class="docutils literal notranslate"><span class="pre">args</span></code> and
@@ -4558,7 +4558,7 @@ <h2>Starting Multiple Workers<a class="headerlink" href="#starting-multiple-work
 <h2>Process Context<a class="headerlink" href="#process-context" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.PContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">PContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">envs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L431"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.PContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">PContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">envs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L431"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.PContext" title="Permalink to this definition">#</a></dt>
 <dd><p>The base class that standardizes operations over a set of processes that are launched via different mechanisms.</p>
 <p>The name <code class="docutils literal notranslate"><span class="pre">PContext</span></code> is intentional to disambiguate with <code class="docutils literal notranslate"><span class="pre">torch.multiprocessing.ProcessContext</span></code>.</p>
 <div class="admonition warning">
@@ -4573,7 +4573,7 @@ <h2>Process Context<a class="headerlink" href="#process-context" title="Permalin
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.MultiprocessContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">MultiprocessContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">envs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_method</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L622"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.MultiprocessContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">MultiprocessContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">envs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_method</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L622"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.MultiprocessContext" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">PContext</span></code> holding worker processes invoked as a function.</p>
 <dl class="field-list simple">
 </dl>
@@ -4581,7 +4581,7 @@ <h2>Process Context<a class="headerlink" href="#process-context" title="Permalin
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.SubprocessContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">SubprocessContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">envs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L808"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.SubprocessContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">SubprocessContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">envs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logs_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_line_prefixes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L808"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.SubprocessContext" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">PContext</span></code> holding worker processes invoked as a binary.</p>
 <dl class="field-list simple">
 </dl>
@@ -4589,7 +4589,7 @@ <h2>Process Context<a class="headerlink" href="#process-context" title="Permalin
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.RunProcsResult">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">RunProcsResult</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">return_values=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">failures=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stdouts=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stderrs=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.RunProcsResult" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">RunProcsResult</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">return_values=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">failures=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stdouts=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stderrs=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.RunProcsResult" title="Permalink to this definition">#</a></dt>
 <dd><p>Results of a completed run of processes started with <code class="docutils literal notranslate"><span class="pre">start_processes()</span></code>. Returned by <code class="docutils literal notranslate"><span class="pre">PContext</span></code>.</p>
 <p>Note the following:</p>
 <ol class="arabic simple">
@@ -4604,7 +4604,7 @@ <h2>Process Context<a class="headerlink" href="#process-context" title="Permalin
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.DefaultLogsSpecs">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">DefaultLogsSpecs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">redirects</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Std.NONE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tee</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Std.NONE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_ranks_filter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.DefaultLogsSpecs" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">DefaultLogsSpecs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">redirects</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Std.NONE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tee</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Std.NONE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_ranks_filter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.DefaultLogsSpecs" title="Permalink to this definition">#</a></dt>
 <dd><p>Default LogsSpecs implementation:</p>
 <ul class="simple">
 <li><p><cite>log_dir</cite> will be created if it doesn’t exist</p></li>
@@ -4614,7 +4614,7 @@ <h2>Process Context<a class="headerlink" href="#process-context" title="Permalin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.DefaultLogsSpecs.reify">
-<span class="sig-name descname"><span class="pre">reify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">envs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L282"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.DefaultLogsSpecs.reify" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">envs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L282"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.DefaultLogsSpecs.reify" title="Permalink to this definition">#</a></dt>
 <dd><p>Uses following scheme to build log destination paths:</p>
 <ul class="simple">
 <li><p><cite>&lt;log_dir&gt;/&lt;rdzv_run_id&gt;/attempt_&lt;attempt&gt;/&lt;rank&gt;/stdout.log</cite></p></li>
@@ -4632,7 +4632,7 @@ <h2>Process Context<a class="headerlink" href="#process-context" title="Permalin
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.LogsDest">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">LogsDest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stdouts=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stderrs=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tee_stdouts=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tee_stderrs=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_files=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.LogsDest" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">LogsDest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stdouts=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stderrs=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tee_stdouts=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tee_stderrs=&lt;factory&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_files=&lt;factory&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.LogsDest" title="Permalink to this definition">#</a></dt>
 <dd><p>For each log type, holds mapping of local rank ids to file paths.</p>
 <dl class="field-list simple">
 </dl>
@@ -4640,7 +4640,7 @@ <h2>Process Context<a class="headerlink" href="#process-context" title="Permalin
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.LogsSpecs">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">LogsSpecs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">redirects</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Std.NONE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tee</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Std.NONE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_ranks_filter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.LogsSpecs" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.api.</span></span><span class="sig-name descname"><span class="pre">LogsSpecs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">redirects</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Std.NONE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tee</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Std.NONE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_ranks_filter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.LogsSpecs" title="Permalink to this definition">#</a></dt>
 <dd><p>Defines logs processing and redirection for each worker process.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4657,7 +4657,7 @@ <h2>Process Context<a class="headerlink" href="#process-context" title="Permalin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.api.LogsSpecs.reify">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">reify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">envs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/api.py#L226"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.LogsSpecs.reify" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">reify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">envs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/api.py#L226"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.api.LogsSpecs.reify" title="Permalink to this definition">#</a></dt>
 <dd><p>Given the environment variables, builds destination of log files for each of the local ranks.</p>
 <p>Envs parameter contains env variables dict for each of the local ranks, where entries are defined in:
 <code class="xref py py-func docutils literal notranslate"><span class="pre">_start_workers()</span></code>.</p>
diff --git a/2.9/elastic/numa.html b/2.9/elastic/numa.html
index 61e8c023b97..29adf83b577 100644
--- a/2.9/elastic/numa.html
+++ b/2.9/elastic/numa.html
@@ -4405,14 +4405,14 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Jul 25, 2025 | Last Updated On: Aug 12, 2025</p>
 <span class="target" id="module-torch.numa.binding"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.numa.binding.AffinityMode">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.numa.binding.</span></span><span class="sig-name descname"><span class="pre">AffinityMode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/numa/binding.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.numa.binding.AffinityMode" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.numa.binding.</span></span><span class="sig-name descname"><span class="pre">AffinityMode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/numa/binding.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.numa.binding.AffinityMode" title="Permalink to this definition">#</a></dt>
 <dd><p>See behavior description for each affinity mode
 in torch.distributed.run.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.numa.binding.NumaOptions">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.numa.binding.</span></span><span class="sig-name descname"><span class="pre">NumaOptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">affinity_mode</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.numa.binding.AffinityMode" title="torch.numa.binding.AffinityMode"><span class="pre">torch.numa.binding.AffinityMode</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">should_fall_back_if_binding_fails</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/numa/binding.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.numa.binding.NumaOptions" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.numa.binding.</span></span><span class="sig-name descname"><span class="pre">NumaOptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">affinity_mode</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.numa.binding.AffinityMode" title="torch.numa.binding.AffinityMode"><span class="pre">torch.numa.binding.AffinityMode</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">should_fall_back_if_binding_fails</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/numa/binding.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.numa.binding.NumaOptions" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -4428,7 +4428,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.numa.binding.maybe_temporarily_apply_numa_binding_to_current_thread">
-<span class="sig-prename descclassname"><span class="pre">torch.numa.binding.</span></span><span class="sig-name descname"><span class="pre">maybe_temporarily_apply_numa_binding_to_current_thread</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gpu_index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/numa/binding.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.numa.binding.maybe_temporarily_apply_numa_binding_to_current_thread" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.numa.binding.</span></span><span class="sig-name descname"><span class="pre">maybe_temporarily_apply_numa_binding_to_current_thread</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gpu_index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/numa/binding.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.numa.binding.maybe_temporarily_apply_numa_binding_to_current_thread" title="Permalink to this definition">#</a></dt>
 <dd><p>1. Applies NUMA binding to the current thread, suitable for the thread
 which will be interacting with GPU gpu_index.
 2. Resets to the original CPU affinity before exiting the context manager.</p>
diff --git a/2.9/elastic/rendezvous.html b/2.9/elastic/rendezvous.html
index f532f34e106..c580324b370 100644
--- a/2.9/elastic/rendezvous.html
+++ b/2.9/elastic/rendezvous.html
@@ -4502,7 +4502,7 @@
 <h2>Registry<a class="headerlink" href="#registry" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousParameters">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousParameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">endpoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_nodes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_nodes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_addr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousParameters" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousParameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">endpoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_nodes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_nodes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_addr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousParameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Hold the parameters to construct a <a class="reference internal" href="#torch.distributed.elastic.rendezvous.RendezvousHandler" title="torch.distributed.elastic.rendezvous.RendezvousHandler"><code class="xref py py-class docutils literal notranslate"><span class="pre">RendezvousHandler</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4519,7 +4519,7 @@ <h2>Registry<a class="headerlink" href="#registry" title="Permalink to this head
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousParameters.get">
-<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L291"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousParameters.get" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L291"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousParameters.get" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the value for <code class="docutils literal notranslate"><span class="pre">key</span></code> if <code class="docutils literal notranslate"><span class="pre">key</span></code> exists, else <code class="docutils literal notranslate"><span class="pre">default</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4530,7 +4530,7 @@ <h2>Registry<a class="headerlink" href="#registry" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousParameters.get_as_bool">
-<span class="sig-name descname"><span class="pre">get_as_bool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousParameters.get_as_bool" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_as_bool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousParameters.get_as_bool" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the value for <code class="docutils literal notranslate"><span class="pre">key</span></code> as a <code class="docutils literal notranslate"><span class="pre">bool</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4541,7 +4541,7 @@ <h2>Registry<a class="headerlink" href="#registry" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousParameters.get_as_int">
-<span class="sig-name descname"><span class="pre">get_as_int</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L314"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousParameters.get_as_int" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_as_int</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L314"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousParameters.get_as_int" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the value for <code class="docutils literal notranslate"><span class="pre">key</span></code> as an <code class="docutils literal notranslate"><span class="pre">int</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4554,7 +4554,7 @@ <h2>Registry<a class="headerlink" href="#registry" title="Permalink to this head
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandlerRegistry">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousHandlerRegistry</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L331"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandlerRegistry" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousHandlerRegistry</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L331"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandlerRegistry" title="Permalink to this definition">#</a></dt>
 <dd><p>Represent a registry of <a class="reference internal" href="#torch.distributed.elastic.rendezvous.RendezvousHandler" title="torch.distributed.elastic.rendezvous.RendezvousHandler"><code class="xref py py-class docutils literal notranslate"><span class="pre">RendezvousHandler</span></code></a> backends.</p>
 <dl class="field-list simple">
 </dl>
@@ -4565,7 +4565,7 @@ <h2>Registry<a class="headerlink" href="#registry" title="Permalink to this head
 <h2>Handler<a class="headerlink" href="#handler" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler" title="Permalink to this definition">#</a></dt>
 <dd><p>Main rendezvous interface.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4575,7 +4575,7 @@ <h2>Handler<a class="headerlink" href="#handler" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandler.get_backend">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_backend</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.get_backend" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_backend</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.get_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the name of the rendezvous backend.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4586,7 +4586,7 @@ <h2>Handler<a class="headerlink" href="#handler" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandler.get_run_id">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_run_id</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.get_run_id" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_run_id</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.get_run_id" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the run id of the rendezvous.</p>
 <p>The run id is a user-defined id that uniquely identifies an instance of
 a distributed application. It typically maps to a job id and is used to
@@ -4600,7 +4600,7 @@ <h2>Handler<a class="headerlink" href="#handler" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandler.is_closed">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">is_closed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.is_closed" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">is_closed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.is_closed" title="Permalink to this definition">#</a></dt>
 <dd><p>Check whether the rendezvous has been closed.</p>
 <p>A closed rendezvous means all future attempts to re-rendezvous within
 same job will fail.</p>
@@ -4618,7 +4618,7 @@ <h2>Handler<a class="headerlink" href="#handler" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandler.next_rendezvous">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">next_rendezvous</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.next_rendezvous" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">next_rendezvous</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.next_rendezvous" title="Permalink to this definition">#</a></dt>
 <dd><p>Main entry-point into the rendezvous barrier.</p>
 <p>Blocks until the rendezvous is complete and the current process is
 included in the formed worker group, or a timeout occurs, or the
@@ -4643,7 +4643,7 @@ <h2>Handler<a class="headerlink" href="#handler" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandler.num_nodes_waiting">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">num_nodes_waiting</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L207"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.num_nodes_waiting" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">num_nodes_waiting</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L207"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.num_nodes_waiting" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the number of nodes who arrived late at the rendezvous
 barrier, hence were not included in the current worker group.</p>
 <p>Callers should periodically call this method to check whether new
@@ -4658,13 +4658,13 @@ <h2>Handler<a class="headerlink" href="#handler" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandler.set_closed">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_closed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.set_closed" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_closed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.set_closed" title="Permalink to this definition">#</a></dt>
 <dd><p>Mark the rendezvous as closed.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousHandler.shutdown">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">shutdown</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L226"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.shutdown" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">shutdown</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L226"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousHandler.shutdown" title="Permalink to this definition">#</a></dt>
 <dd><p>Close all resources that were open for the rendezvous.</p>
 <p>Example:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">rdzv_handler</span> <span class="o">=</span> <span class="o">...</span>
@@ -4697,7 +4697,7 @@ <h2>Handler<a class="headerlink" href="#handler" title="Permalink to this headin
 <h2>Dataclasses<a class="headerlink" href="#dataclasses" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.RendezvousInfo">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousInfo</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">world_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bootstrap_store_info</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousInfo" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousInfo</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">world_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bootstrap_store_info</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L108"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.RendezvousInfo" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds the information about the rendezvous.</p>
 <dl class="field-list simple">
 </dl>
@@ -4705,13 +4705,13 @@ <h2>Dataclasses<a class="headerlink" href="#dataclasses" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.api.RendezvousStoreInfo">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousStoreInfo</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">master_addr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">master_port</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousStoreInfo" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousStoreInfo</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">master_addr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">master_port</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousStoreInfo" title="Permalink to this definition">#</a></dt>
 <dd><p>Store address and port that can be used to bootstrap trainer distributed comms</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.api.RendezvousStoreInfo.build">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">build</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">store</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousStoreInfo.build" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">build</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rank</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">store</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousStoreInfo.build" title="Permalink to this definition">#</a></dt>
 <dd><p>Factory method, finds unused new port on rank0 host and addr/port info with all ranks.</p>
 <p>If master_addr/master_port is knowns (useful when sharing existing tcp store server) use the constructor.</p>
 <dl class="field-list simple">
@@ -4736,37 +4736,37 @@ <h2>Dataclasses<a class="headerlink" href="#dataclasses" title="Permalink to thi
 <h2>Exceptions<a class="headerlink" href="#exceptions" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.api.RendezvousError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousError" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents the base type for rendezvous errors.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.api.RendezvousClosedError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousClosedError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousClosedError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousClosedError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousClosedError" title="Permalink to this definition">#</a></dt>
 <dd><p>Raised when a rendezvous is closed.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.api.RendezvousTimeoutError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousTimeoutError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousTimeoutError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousTimeoutError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousTimeoutError" title="Permalink to this definition">#</a></dt>
 <dd><p>Raised when a rendezvous did not complete on time.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.api.RendezvousConnectionError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousConnectionError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousConnectionError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousConnectionError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousConnectionError" title="Permalink to this definition">#</a></dt>
 <dd><p>Raised when the connection to a rendezvous backend has failed.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.api.RendezvousStateError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousStateError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousStateError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousStateError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L50"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousStateError" title="Permalink to this definition">#</a></dt>
 <dd><p>Raised when the state of a rendezvous is corrupt.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.api.RendezvousGracefulExitError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousGracefulExitError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/api.py#L54"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousGracefulExitError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.api.</span></span><span class="sig-name descname"><span class="pre">RendezvousGracefulExitError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/api.py#L54"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.api.RendezvousGracefulExitError" title="Permalink to this definition">#</a></dt>
 <dd><p>Raised when node wasn’t not included in rendezvous and gracefully exits.</p>
 <p>Exception is a mechanism to exit the stack, however does not mean a failure.</p>
 </dd></dl>
@@ -4778,7 +4778,7 @@ <h2>Implementations<a class="headerlink" href="#implementations" title="Permalin
 <h3>Dynamic Rendezvous<a class="headerlink" href="#dynamic-rendezvous" title="Permalink to this heading">#</a></h3>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.dynamic_rendezvous.create_handler">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.dynamic_rendezvous.</span></span><span class="sig-name descname"><span class="pre">create_handler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L1388"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.create_handler" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.dynamic_rendezvous.</span></span><span class="sig-name descname"><span class="pre">create_handler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L1388"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.create_handler" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a new <a class="reference internal" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler" title="torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler"><code class="xref py py-class docutils literal notranslate"><span class="pre">DynamicRendezvousHandler</span></code></a> from the specified parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4830,13 +4830,13 @@ <h3>Dynamic Rendezvous<a class="headerlink" href="#dynamic-rendezvous" title="Pe
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.dynamic_rendezvous.</span></span><span class="sig-name descname"><span class="pre">DynamicRendezvousHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L995"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.dynamic_rendezvous.</span></span><span class="sig-name descname"><span class="pre">DynamicRendezvousHandler</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L995"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler" title="Permalink to this definition">#</a></dt>
 <dd><p>Represent a handler that sets up a rendezvous among a set of nodes.</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler.from_backend">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_nodes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_nodes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_addr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_alive_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_alive_max_attempt</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L1010"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler.from_backend" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_nodes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_nodes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_addr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_alive_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_alive_max_attempt</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L1010"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler.from_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a new <a class="reference internal" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler" title="torch.distributed.elastic.rendezvous.dynamic_rendezvous.DynamicRendezvousHandler"><code class="xref py py-class docutils literal notranslate"><span class="pre">DynamicRendezvousHandler</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4861,11 +4861,11 @@ <h3>Dynamic Rendezvous<a class="headerlink" href="#dynamic-rendezvous" title="Pe
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.dynamic_rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousBackend</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.dynamic_rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousBackend</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend" title="Permalink to this definition">#</a></dt>
 <dd><p>Represent a backend that holds the rendezvous state.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend.get_state">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend.get_state" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend.get_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the rendezvous state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4892,7 +4892,7 @@ <h3>Dynamic Rendezvous<a class="headerlink" href="#dynamic-rendezvous" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend.set_state">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend.set_state" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousBackend.set_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the rendezvous state.</p>
 <p>The new rendezvous state is set conditionally:</p>
 <blockquote>
@@ -4937,7 +4937,7 @@ <h3>Dynamic Rendezvous<a class="headerlink" href="#dynamic-rendezvous" title="Pe
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousTimeout">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.dynamic_rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousTimeout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">join</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">close</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">heartbeat</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousTimeout" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.dynamic_rendezvous.</span></span><span class="sig-name descname"><span class="pre">RendezvousTimeout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">join</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">close</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">heartbeat</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/dynamic_rendezvous.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.dynamic_rendezvous.RendezvousTimeout" title="Permalink to this definition">#</a></dt>
 <dd><p>Hold the timeout configuration of a rendezvous.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4983,7 +4983,7 @@ <h3>Dynamic Rendezvous<a class="headerlink" href="#dynamic-rendezvous" title="Pe
 <h4>C10d Backend<a class="headerlink" href="#c10d-backend" title="Permalink to this heading">#</a></h4>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.create_backend">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.</span></span><span class="sig-name descname"><span class="pre">create_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.create_backend" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.</span></span><span class="sig-name descname"><span class="pre">create_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.create_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a new <a class="reference internal" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend" title="torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend"><code class="xref py py-class docutils literal notranslate"><span class="pre">C10dRendezvousBackend</span></code></a> from the specified parameters.</p>
 <div class="pst-scrollable-table-container"><table class="table">
 <colgroup>
@@ -5038,7 +5038,7 @@ <h4>C10d Backend<a class="headerlink" href="#c10d-backend" title="Permalink to t
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.</span></span><span class="sig-name descname"><span class="pre">C10dRendezvousBackend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.</span></span><span class="sig-name descname"><span class="pre">C10dRendezvousBackend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">store</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents a C10d-backed rendezvous backend.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5051,7 +5051,7 @@ <h4>C10d Backend<a class="headerlink" href="#c10d-backend" title="Permalink to t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend.get_state">
-<span class="sig-name descname"><span class="pre">get_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend.get_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend.get_state" title="Permalink to this definition">#</a></dt>
 <dd><p>See base class.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5068,7 +5068,7 @@ <h4>C10d Backend<a class="headerlink" href="#c10d-backend" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend.set_state">
-<span class="sig-name descname"><span class="pre">set_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend.set_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.c10d_rendezvous_backend.C10dRendezvousBackend.set_state" title="Permalink to this definition">#</a></dt>
 <dd><p>See base class.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5084,7 +5084,7 @@ <h4>C10d Backend<a class="headerlink" href="#c10d-backend" title="Permalink to t
 <h4>Etcd Backend<a class="headerlink" href="#etcd-backend" title="Permalink to this heading">#</a></h4>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.create_backend">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.</span></span><span class="sig-name descname"><span class="pre">create_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.create_backend" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.</span></span><span class="sig-name descname"><span class="pre">create_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.create_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a new <a class="reference internal" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend" title="torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend"><code class="xref py py-class docutils literal notranslate"><span class="pre">EtcdRendezvousBackend</span></code></a> from the specified parameters.</p>
 <div class="pst-scrollable-table-container"><table class="table">
 <colgroup>
@@ -5129,7 +5129,7 @@ <h4>Etcd Backend<a class="headerlink" href="#etcd-backend" title="Permalink to t
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.</span></span><span class="sig-name descname"><span class="pre">EtcdRendezvousBackend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">client</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ttl</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.</span></span><span class="sig-name descname"><span class="pre">EtcdRendezvousBackend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">client</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ttl</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents an etcd-based rendezvous backend.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5143,7 +5143,7 @@ <h4>Etcd Backend<a class="headerlink" href="#etcd-backend" title="Permalink to t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend.get_state">
-<span class="sig-name descname"><span class="pre">get_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend.get_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend.get_state" title="Permalink to this definition">#</a></dt>
 <dd><p>See base class.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5160,7 +5160,7 @@ <h4>Etcd Backend<a class="headerlink" href="#etcd-backend" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend.set_state">
-<span class="sig-name descname"><span class="pre">set_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend.set_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous_backend.EtcdRendezvousBackend.set_state" title="Permalink to this definition">#</a></dt>
 <dd><p>See base class.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5183,7 +5183,7 @@ <h3>Etcd Rendezvous (Legacy)<a class="headerlink" href="#etcd-rendezvous-legacy"
 </div>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_rendezvous.EtcdRendezvousHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_rendezvous.</span></span><span class="sig-name descname"><span class="pre">EtcdRendezvousHandler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rdzv_impl</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_addr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_rendezvous.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous.EtcdRendezvousHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_rendezvous.</span></span><span class="sig-name descname"><span class="pre">EtcdRendezvousHandler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">rdzv_impl</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_addr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_rendezvous.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_rendezvous.EtcdRendezvousHandler" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements a
 <a class="reference internal" href="#torch.distributed.elastic.rendezvous.RendezvousHandler" title="torch.distributed.elastic.rendezvous.RendezvousHandler"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.distributed.elastic.rendezvous.RendezvousHandler</span></code></a> interface
 backed by
@@ -5269,14 +5269,14 @@ <h3>Etcd Store<a class="headerlink" href="#etcd-store" title="Permalink to this
 <code class="docutils literal notranslate"><span class="pre">next_rendezvous()</span></code> when etcd is used as the rendezvous backend.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_store.EtcdStore">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_store.</span></span><span class="sig-name descname"><span class="pre">EtcdStore</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">etcd_client</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etcd_store_prefix</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_store.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_store.</span></span><span class="sig-name descname"><span class="pre">EtcdStore</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">etcd_client</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etcd_store_prefix</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_store.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore" title="Permalink to this definition">#</a></dt>
 <dd><p>Implement a c10 Store interface by piggybacking on the rendezvous etcd instance.</p>
 <p>This is the store object returned by <code class="docutils literal notranslate"><span class="pre">EtcdRendezvous</span></code>.</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.add">
-<span class="sig-name descname"><span class="pre">add</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_store.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.add" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_store.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.add" title="Permalink to this definition">#</a></dt>
 <dd><p>Atomically increment a value by an integer amount.</p>
 <p>The integer is represented as a string using base 10. If key is not present,
 a default value of <code class="docutils literal notranslate"><span class="pre">0</span></code> will be assumed.</p>
@@ -5292,7 +5292,7 @@ <h3>Etcd Store<a class="headerlink" href="#etcd-store" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.check">
-<span class="sig-name descname"><span class="pre">check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_store.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.check" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">check</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_store.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.check" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if all of the keys are immediately present (without waiting).</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5303,7 +5303,7 @@ <h3>Etcd Store<a class="headerlink" href="#etcd-store" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.get">
-<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_store.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.get" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_store.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.get" title="Permalink to this definition">#</a></dt>
 <dd><p>Get a value by key, possibly doing a blocking wait.</p>
 <p>If key is not immediately present, will do a blocking wait
 for at most <code class="docutils literal notranslate"><span class="pre">timeout</span></code> duration or until the key is published.</p>
@@ -5322,14 +5322,14 @@ <h3>Etcd Store<a class="headerlink" href="#etcd-store" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.set">
-<span class="sig-name descname"><span class="pre">set</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_store.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.set" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_store.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.set" title="Permalink to this definition">#</a></dt>
 <dd><p>Write a key/value pair into <code class="docutils literal notranslate"><span class="pre">EtcdStore</span></code>.</p>
 <p>Both key and value may be either Python <code class="docutils literal notranslate"><span class="pre">str</span></code> or <code class="docutils literal notranslate"><span class="pre">bytes</span></code>.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.wait">
-<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">override_timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_store.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.wait" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">override_timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_store.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_store.EtcdStore.wait" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait until all of the keys are published, or until timeout.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Raises</dt>
@@ -5355,7 +5355,7 @@ <h3>Etcd Server<a class="headerlink" href="#etcd-server" title="Permalink to thi
 </div>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.rendezvous.etcd_server.EtcdServer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_server.</span></span><span class="sig-name descname"><span class="pre">EtcdServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/rendezvous/etcd_server.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_server.EtcdServer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.rendezvous.etcd_server.</span></span><span class="sig-name descname"><span class="pre">EtcdServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/rendezvous/etcd_server.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.rendezvous.etcd_server.EtcdServer" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition note">
 <p class="admonition-title">Note</p>
 <p>tested on etcd server v3.4.3.</p>
diff --git a/2.9/elastic/subprocess_handler.html b/2.9/elastic/subprocess_handler.html
index 711742f4e09..acff148ca7f 100644
--- a/2.9/elastic/subprocess_handler.html
+++ b/2.9/elastic/subprocess_handler.html
@@ -4407,7 +4407,7 @@
 <h2>Retrieve SubprocessHandler<a class="headerlink" href="#retrieve-subprocesshandler" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.subprocess_handler.handlers.get_subprocess_handler">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.subprocess_handler.handlers.</span></span><span class="sig-name descname"><span class="pre">get_subprocess_handler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stdout</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stderr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_rank_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/subprocess_handler/handlers.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.subprocess_handler.handlers.get_subprocess_handler" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.subprocess_handler.handlers.</span></span><span class="sig-name descname"><span class="pre">get_subprocess_handler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stdout</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stderr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_rank_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/subprocess_handler/handlers.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.subprocess_handler.handlers.get_subprocess_handler" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="#torch.distributed.elastic.multiprocessing.subprocess_handler.subprocess_handler.SubprocessHandler" title="torch.distributed.elastic.multiprocessing.subprocess_handler.subprocess_handler.SubprocessHandler"><em>SubprocessHandler</em></a></p>
@@ -4420,7 +4420,7 @@ <h2>Retrieve SubprocessHandler<a class="headerlink" href="#retrieve-subprocessha
 <h2>SubprocessHandler<a class="headerlink" href="#subprocesshandler" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.multiprocessing.subprocess_handler.subprocess_handler.SubprocessHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.subprocess_handler.subprocess_handler.</span></span><span class="sig-name descname"><span class="pre">SubprocessHandler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stdout</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stderr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_rank_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/multiprocessing/subprocess_handler/subprocess_handler.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.subprocess_handler.subprocess_handler.SubprocessHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.multiprocessing.subprocess_handler.subprocess_handler.</span></span><span class="sig-name descname"><span class="pre">SubprocessHandler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">entrypoint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stdout</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stderr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">local_rank_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">numa_options</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/multiprocessing/subprocess_handler/subprocess_handler.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.multiprocessing.subprocess_handler.subprocess_handler.SubprocessHandler" title="Permalink to this definition">#</a></dt>
 <dd><p>Convenience wrapper around python’s <code class="docutils literal notranslate"><span class="pre">subprocess.Popen</span></code>. Keeps track of
 meta-objects associated to the process (e.g. stdout and stderr redirect fds).</p>
 <dl class="field-list simple">
diff --git a/2.9/elastic/timer.html b/2.9/elastic/timer.html
index 89c1017442e..1ed29bf1d7c 100644
--- a/2.9/elastic/timer.html
+++ b/2.9/elastic/timer.html
@@ -4438,7 +4438,7 @@
 <h2>Client Methods<a class="headerlink" href="#client-methods" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.configure">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">configure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timer_client</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.configure" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">configure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timer_client</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.configure" title="Permalink to this definition">#</a></dt>
 <dd><p>Configures a timer client. Must be called before using <code class="docutils literal notranslate"><span class="pre">expires</span></code>.</p>
 <dl class="field-list simple">
 </dl>
@@ -4446,7 +4446,7 @@ <h2>Client Methods<a class="headerlink" href="#client-methods" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.expires">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">expires</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">after</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">client</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.expires" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">expires</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">after</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">client</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.expires" title="Permalink to this definition">#</a></dt>
 <dd><p>Acquires a countdown timer that expires in <code class="docutils literal notranslate"><span class="pre">after</span></code> seconds from now,
 unless the code-block that it wraps is finished within the timeframe.
 When the timer expires, this worker is eligible to be reaped. The
@@ -4480,7 +4480,7 @@ <h2>Server/Client Implementations<a class="headerlink" href="#server-client-impl
 a <code class="docutils literal notranslate"><span class="pre">multiprocess.Queue</span></code>.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.LocalTimerServer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">LocalTimerServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mp_queue</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">60</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">daemon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/local_timer.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.LocalTimerServer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">LocalTimerServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mp_queue</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">60</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">daemon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/local_timer.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.LocalTimerServer" title="Permalink to this definition">#</a></dt>
 <dd><p>Server that works with <code class="docutils literal notranslate"><span class="pre">LocalTimerClient</span></code>. Clients are expected to be
 subprocesses to the parent process that is running this server. Each host
 in the job is expected to start its own timer server locally and each
@@ -4492,7 +4492,7 @@ <h2>Server/Client Implementations<a class="headerlink" href="#server-client-impl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.LocalTimerClient">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">LocalTimerClient</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mp_queue</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/local_timer.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.LocalTimerClient" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">LocalTimerClient</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mp_queue</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/local_timer.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.LocalTimerClient" title="Permalink to this definition">#</a></dt>
 <dd><p>Client side of <code class="docutils literal notranslate"><span class="pre">LocalTimerServer</span></code>. This client is meant to be used
 on the same host that the <code class="docutils literal notranslate"><span class="pre">LocalTimerServer</span></code> is running on and uses
 pid to uniquely identify a worker. This is particularly useful in situations
@@ -4504,7 +4504,7 @@ <h2>Server/Client Implementations<a class="headerlink" href="#server-client-impl
 based on a named pipe.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.FileTimerServer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">FileTimerServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">daemon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_event</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/file_based_local_timer.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.FileTimerServer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">FileTimerServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_interval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">daemon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_event</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/file_based_local_timer.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.FileTimerServer" title="Permalink to this definition">#</a></dt>
 <dd><p>Server that works with <code class="docutils literal notranslate"><span class="pre">FileTimerClient</span></code>. Clients are expected to be
 running on the same host as the process that is running this server.
 Each host in the job is expected to start its own timer server locally
@@ -4526,7 +4526,7 @@ <h2>Server/Client Implementations<a class="headerlink" href="#server-client-impl
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.FileTimerClient">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">FileTimerClient</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">signal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Signals.SIGKILL</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/file_based_local_timer.py#L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.FileTimerClient" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">FileTimerClient</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">signal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">Signals.SIGKILL</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/file_based_local_timer.py#L104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.FileTimerClient" title="Permalink to this definition">#</a></dt>
 <dd><p>Client side of <code class="docutils literal notranslate"><span class="pre">FileTimerServer</span></code>. This client is meant to be used
 on the same host that the <code class="docutils literal notranslate"><span class="pre">FileTimerServer</span></code> is running on and uses
 pid to uniquely identify a worker.
@@ -4556,7 +4556,7 @@ <h2>Writing a custom timer server/client<a class="headerlink" href="#writing-a-c
 the server and client.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.TimerRequest">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">TimerRequest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scope_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expiration_time</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerRequest" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">TimerRequest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scope_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expiration_time</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerRequest" title="Permalink to this definition">#</a></dt>
 <dd><p>Data object representing a countdown timer acquisition and release
 that is used between the <code class="docutils literal notranslate"><span class="pre">TimerClient</span></code> and <code class="docutils literal notranslate"><span class="pre">TimerServer</span></code>.
 A negative <code class="docutils literal notranslate"><span class="pre">expiration_time</span></code> should be interpreted as a “release”
@@ -4573,7 +4573,7 @@ <h2>Writing a custom timer server/client<a class="headerlink" href="#writing-a-c
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.TimerServer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">TimerServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">request_queue</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_interval</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">daemon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerServer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">TimerServer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">request_queue</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_interval</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">daemon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerServer" title="Permalink to this definition">#</a></dt>
 <dd><p>Entity that monitors active timers and expires them
 in a timely fashion. This server is responsible for
 reaping workers that have expired timers.</p>
@@ -4581,7 +4581,7 @@ <h2>Writing a custom timer server/client<a class="headerlink" href="#writing-a-c
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.TimerServer.clear_timers">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">clear_timers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_ids</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L145"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerServer.clear_timers" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">clear_timers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_ids</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L145"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerServer.clear_timers" title="Permalink to this definition">#</a></dt>
 <dd><p>Clears all timers for the given <code class="docutils literal notranslate"><span class="pre">worker_ids</span></code>.</p>
 <dl class="field-list simple">
 </dl>
@@ -4589,7 +4589,7 @@ <h2>Writing a custom timer server/client<a class="headerlink" href="#writing-a-c
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.TimerServer.get_expired_timers">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_expired_timers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">deadline</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerServer.get_expired_timers" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_expired_timers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">deadline</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerServer.get_expired_timers" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns all expired timers for each worker_id. An expired timer
 is a timer for which the expiration_time is less than or equal to
 the provided deadline.</p>
@@ -4602,7 +4602,7 @@ <h2>Writing a custom timer server/client<a class="headerlink" href="#writing-a-c
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.TimerServer.register_timers">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">register_timers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timer_requests</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerServer.register_timers" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">register_timers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timer_requests</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerServer.register_timers" title="Permalink to this definition">#</a></dt>
 <dd><p>Processes the incoming timer requests and registers them with the server.
 The timer request can either be a acquire-timer or release-timer request.
 Timer requests with a negative expiration_time should be interpreted
@@ -4615,12 +4615,12 @@ <h2>Writing a custom timer server/client<a class="headerlink" href="#writing-a-c
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.TimerClient">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">TimerClient</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerClient" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.</span></span><span class="sig-name descname"><span class="pre">TimerClient</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerClient" title="Permalink to this definition">#</a></dt>
 <dd><p>Client library to acquire and release countdown timers by communicating
 with the TimerServer.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.TimerClient.acquire">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">acquire</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scope_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expiration_time</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerClient.acquire" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">acquire</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scope_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expiration_time</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerClient.acquire" title="Permalink to this definition">#</a></dt>
 <dd><p>Acquires a timer for the worker that holds this client object
 given the scope_id and expiration_time. Typically registers
 the timer with the TimerServer.</p>
@@ -4630,7 +4630,7 @@ <h2>Writing a custom timer server/client<a class="headerlink" href="#writing-a-c
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.TimerClient.release">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">release</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scope_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/api.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerClient.release" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">release</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scope_id</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/api.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.TimerClient.release" title="Permalink to this definition">#</a></dt>
 <dd><p>Releases the timer for the <code class="docutils literal notranslate"><span class="pre">scope_id</span></code> on the worker this
 client represents. After this method is
 called, the countdown timer on the scope is no longer in effect.</p>
@@ -4645,7 +4645,7 @@ <h2>Writing a custom timer server/client<a class="headerlink" href="#writing-a-c
 <span id="debug-info-logging"></span><h2>Debug info logging<a class="headerlink" href="#module-torch.distributed.elastic.timer.debug_info_logging" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.elastic.timer.debug_info_logging.log_debug_info_for_expired_timers">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.debug_info_logging.</span></span><span class="sig-name descname"><span class="pre">log_debug_info_for_expired_timers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expired_timers</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/elastic/timer/debug_info_logging.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.debug_info_logging.log_debug_info_for_expired_timers" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.elastic.timer.debug_info_logging.</span></span><span class="sig-name descname"><span class="pre">log_debug_info_for_expired_timers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">run_id</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expired_timers</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/elastic/timer/debug_info_logging.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.elastic.timer.debug_info_logging.log_debug_info_for_expired_timers" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
diff --git a/2.9/export/api_reference.html b/2.9/export/api_reference.html
index 48ec22a5d6a..c838ac24260 100644
--- a/2.9/export/api_reference.html
+++ b/2.9/export/api_reference.html
@@ -4405,7 +4405,7 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Jul 17, 2025 | Last Updated On: Jul 17, 2025</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.export">
-<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserve_module_call_signature</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefer_deferred_runtime_asserts_over_guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/__init__.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.export" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserve_module_call_signature</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefer_deferred_runtime_asserts_over_guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/__init__.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.export" title="Permalink to this definition">#</a></dt>
 <dd><p><a class="reference internal" href="#torch.export.export" title="torch.export.export"><code class="xref py py-func docutils literal notranslate"><span class="pre">export()</span></code></a> takes any nn.Module along with example inputs, and produces a traced graph representing
 only the Tensor computation of the function in an Ahead-of-Time (AOT) fashion,
 which can subsequently be executed with different inputs or serialized.  The
@@ -4492,7 +4492,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.ExportedProgram">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">ExportedProgram</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_signature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">range_constraints</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_call_graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constants</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verifiers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L1010"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">ExportedProgram</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_signature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">range_constraints</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_call_graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constants</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verifiers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L1010"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram" title="Permalink to this definition">#</a></dt>
 <dd><p>Package of a program from <a class="reference internal" href="#torch.export.export" title="torch.export.export"><code class="xref py py-func docutils literal notranslate"><span class="pre">export()</span></code></a>. It contains
 an <a class="reference internal" href="../fx.html#torch.fx.Graph" title="torch.fx.Graph"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.fx.Graph</span></code></a> that represents Tensor computation, a state_dict containing
 tensor values of all lifted parameters and buffers, and various metadata.</p>
@@ -4507,7 +4507,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.ExportedProgram.buffers">
-<span class="sig-name descname"><span class="pre">buffers</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L1148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">buffers</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L1148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns an iterator over original module buffers.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -4585,7 +4585,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.ExportedProgram.module">
-<span class="sig-name descname"><span class="pre">module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">check_guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L1386"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">check_guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L1386"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.module" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a self contained GraphModule with all the parameters/buffers inlined.</p>
 <ul class="simple">
 <li><p>When <cite>check_guards=True</cite> (default), a <cite>_guards_fn</cite> submodule is generated
@@ -4612,7 +4612,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.ExportedProgram.named_buffers">
-<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L1156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.named_buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L1156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.named_buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns an iterator over original module buffers, yielding
 both the name of the buffer as well as the buffer itself.</p>
 <div class="admonition warning">
@@ -4628,7 +4628,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.ExportedProgram.named_parameters">
-<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L1139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.named_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L1139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.named_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns an iterator over original module parameters, yielding
 both the name of the parameter as well as the parameter itself.</p>
 <div class="admonition warning">
@@ -4644,7 +4644,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.ExportedProgram.parameters">
-<span class="sig-name descname"><span class="pre">parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L1131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L1131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns an iterator over original module’s parameters.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -4668,7 +4668,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.ExportedProgram.run_decompositions">
-<span class="sig-name descname"><span class="pre">run_decompositions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decomp_table</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decompose_custom_triton_ops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L1421"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.run_decompositions" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">run_decompositions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decomp_table</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decompose_custom_triton_ops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L1421"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.run_decompositions" title="Permalink to this definition">#</a></dt>
 <dd><p>Run a set of decompositions on the exported program and returns a new
 exported program. By default we will run the Core ATen decompositions to
 get operators in the
@@ -4719,7 +4719,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.ExportedProgram.validate">
-<span class="sig-name descname"><span class="pre">validate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L1597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.validate" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">validate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L1597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.ExportedProgram.validate" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This API is experimental and is <em>NOT</em> backward-compatible.</p>
@@ -4748,7 +4748,7 @@
 
 <span class="target" id="module-torch.export.dynamic_shapes"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.export.dynamic_shapes.AdditionalInputs">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.dynamic_shapes.</span></span><span class="sig-name descname"><span class="pre">AdditionalInputs</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/dynamic_shapes.py#L800"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.AdditionalInputs" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.dynamic_shapes.</span></span><span class="sig-name descname"><span class="pre">AdditionalInputs</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/dynamic_shapes.py#L800"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.AdditionalInputs" title="Permalink to this definition">#</a></dt>
 <dd><p>Infers dynamic_shapes based on additional inputs.</p>
 <p>This is useful particularly for deployment engineers who, on the one hand, may
 have access to ample testing or profiling data that can provide a fair sense of
@@ -4772,13 +4772,13 @@
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.dynamic_shapes.AdditionalInputs.add">
-<span class="sig-name descname"><span class="pre">add</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/dynamic_shapes.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.AdditionalInputs.add" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/dynamic_shapes.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.AdditionalInputs.add" title="Permalink to this definition">#</a></dt>
 <dd><p>Additional input <code class="xref py py-func docutils literal notranslate"><span class="pre">args()</span></code> and <code class="xref py py-func docutils literal notranslate"><span class="pre">kwargs()</span></code>.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.dynamic_shapes.AdditionalInputs.dynamic_shapes">
-<span class="sig-name descname"><span class="pre">dynamic_shapes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/dynamic_shapes.py#L841"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.AdditionalInputs.dynamic_shapes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">dynamic_shapes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/dynamic_shapes.py#L841"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.AdditionalInputs.dynamic_shapes" title="Permalink to this definition">#</a></dt>
 <dd><p>Infers a <a class="reference internal" href="#torch.export.dynamic_shapes.AdditionalInputs.dynamic_shapes" title="torch.export.dynamic_shapes.AdditionalInputs.dynamic_shapes"><code class="xref py py-func docutils literal notranslate"><span class="pre">dynamic_shapes()</span></code></a> pytree structure by merging shapes of the
 original input <code class="xref py py-func docutils literal notranslate"><span class="pre">args()</span></code> and <code class="xref py py-func docutils literal notranslate"><span class="pre">kwargs()</span></code> and of each additional input
 args and kwargs.</p>
@@ -4786,7 +4786,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.dynamic_shapes.AdditionalInputs.verify">
-<span class="sig-name descname"><span class="pre">verify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ep</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/dynamic_shapes.py#L883"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.AdditionalInputs.verify" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">verify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ep</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/dynamic_shapes.py#L883"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.AdditionalInputs.verify" title="Permalink to this definition">#</a></dt>
 <dd><p>Verifies that an exported program is valid for each additional input.</p>
 </dd></dl>
 
@@ -4794,7 +4794,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.dynamic_shapes.Dim">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.dynamic_shapes.</span></span><span class="sig-name descname"><span class="pre">Dim</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/dynamic_shapes.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.Dim" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.dynamic_shapes.</span></span><span class="sig-name descname"><span class="pre">Dim</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/dynamic_shapes.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.Dim" title="Permalink to this definition">#</a></dt>
 <dd><p>The <code class="docutils literal notranslate"><span class="pre">Dim</span></code> class allows users to specify dynamism in their exported
 programs. By marking a dimension with a <code class="docutils literal notranslate"><span class="pre">Dim</span></code>, the compiler associates the
 dimension with a symbolic integer containing a dynamic range.</p>
@@ -4855,7 +4855,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.dynamic_shapes.ShapesCollection">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.dynamic_shapes.</span></span><span class="sig-name descname"><span class="pre">ShapesCollection</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/dynamic_shapes.py#L705"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.ShapesCollection" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.dynamic_shapes.</span></span><span class="sig-name descname"><span class="pre">ShapesCollection</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/dynamic_shapes.py#L705"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.ShapesCollection" title="Permalink to this definition">#</a></dt>
 <dd><p>Builder for dynamic_shapes.
 Used to assign dynamic shape specifications to tensors that appear in inputs.</p>
 <p>This is useful particularly when <code class="xref py py-func docutils literal notranslate"><span class="pre">args()</span></code> is a nested input structure, and it’s
@@ -4893,7 +4893,7 @@
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.dynamic_shapes.ShapesCollection.dynamic_shapes">
-<span class="sig-name descname"><span class="pre">dynamic_shapes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/dynamic_shapes.py#L774"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.ShapesCollection.dynamic_shapes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">dynamic_shapes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/dynamic_shapes.py#L774"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.ShapesCollection.dynamic_shapes" title="Permalink to this definition">#</a></dt>
 <dd><p>Generates the <a class="reference internal" href="#torch.export.dynamic_shapes.ShapesCollection.dynamic_shapes" title="torch.export.dynamic_shapes.ShapesCollection.dynamic_shapes"><code class="xref py py-func docutils literal notranslate"><span class="pre">dynamic_shapes()</span></code></a> pytree structure according to <code class="xref py py-func docutils literal notranslate"><span class="pre">args()</span></code> and <code class="xref py py-func docutils literal notranslate"><span class="pre">kwargs()</span></code>.</p>
 </dd></dl>
 
@@ -4901,7 +4901,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.dynamic_shapes.refine_dynamic_shapes_from_suggested_fixes">
-<span class="sig-prename descclassname"><span class="pre">torch.export.dynamic_shapes.</span></span><span class="sig-name descname"><span class="pre">refine_dynamic_shapes_from_suggested_fixes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/dynamic_shapes.py#L1234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.refine_dynamic_shapes_from_suggested_fixes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.dynamic_shapes.</span></span><span class="sig-name descname"><span class="pre">refine_dynamic_shapes_from_suggested_fixes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/dynamic_shapes.py#L1234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.dynamic_shapes.refine_dynamic_shapes_from_suggested_fixes" title="Permalink to this definition">#</a></dt>
 <dd><p>When exporting with <code class="xref py py-func docutils literal notranslate"><span class="pre">dynamic_shapes()</span></code>, export may fail with a ConstraintViolation error if the specification
 doesn’t match the constraints inferred from tracing the model. The error message may provide suggested fixes -
 changes that can be made to <code class="xref py py-func docutils literal notranslate"><span class="pre">dynamic_shapes()</span></code> to export successfully.</p>
@@ -4934,7 +4934,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.save">
-<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ep</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/__init__.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.save" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ep</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/__init__.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.save" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>Under active development, saved files may not be usable in newer versions
@@ -4983,7 +4983,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.load">
-<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected_opset_version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/__init__.py#L389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.load" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected_opset_version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/__init__.py#L389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.load" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>Under active development, saved files may not be usable in newer versions
@@ -5034,7 +5034,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.pt2_archive._package.package_pt2">
-<span class="sig-prename descclassname"><span class="pre">torch.export.pt2_archive._package.</span></span><span class="sig-name descname"><span class="pre">package_pt2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exported_programs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">aoti_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive._package.package_pt2" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.pt2_archive._package.</span></span><span class="sig-name descname"><span class="pre">package_pt2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exported_programs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">aoti_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive._package.package_pt2" title="Permalink to this definition">#</a></dt>
 <dd><p>Saves the artifacts to a PT2Archive format. The artifact can then be loaded
 using <code class="docutils literal notranslate"><span class="pre">load_pt2</span></code>.</p>
 <dl class="field-list simple">
@@ -5067,7 +5067,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.pt2_archive._package.load_pt2">
-<span class="sig-prename descclassname"><span class="pre">torch.export.pt2_archive._package.</span></span><span class="sig-name descname"><span class="pre">load_pt2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected_opset_version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_single_threaded</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_runners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">load_weights_from_disk</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L902"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive._package.load_pt2" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.pt2_archive._package.</span></span><span class="sig-name descname"><span class="pre">load_pt2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected_opset_version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_single_threaded</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_runners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">load_weights_from_disk</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L902"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive._package.load_pt2" title="Permalink to this definition">#</a></dt>
 <dd><p>Loads all the artifacts previously saved with <code class="docutils literal notranslate"><span class="pre">package_pt2</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5097,7 +5097,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.draft_export">
-<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">draft_export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserve_module_call_signature</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefer_deferred_runtime_asserts_over_guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/__init__.py#L535"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.draft_export" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">draft_export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserve_module_call_signature</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefer_deferred_runtime_asserts_over_guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/__init__.py#L535"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.draft_export" title="Permalink to this definition">#</a></dt>
 <dd><p>A version of torch.export.export which is designed to consistently produce
 an ExportedProgram, even if there are potential soundness issues, and to
 generate a report listing the issues found.</p>
@@ -5110,11 +5110,11 @@
 
 <span class="target" id="module-torch.export.unflatten"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.export.unflatten.FlatArgsAdapter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.unflatten.</span></span><span class="sig-name descname"><span class="pre">FlatArgsAdapter</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/unflatten.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.FlatArgsAdapter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.unflatten.</span></span><span class="sig-name descname"><span class="pre">FlatArgsAdapter</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/unflatten.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.FlatArgsAdapter" title="Permalink to this definition">#</a></dt>
 <dd><p>Adapts input arguments with <code class="docutils literal notranslate"><span class="pre">input_spec</span></code> to align <code class="docutils literal notranslate"><span class="pre">target_spec</span></code>.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.unflatten.FlatArgsAdapter.adapt">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">adapt</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target_spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/unflatten.py#L286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.FlatArgsAdapter.adapt" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">adapt</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target_spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_spec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/unflatten.py#L286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.FlatArgsAdapter.adapt" title="Permalink to this definition">#</a></dt>
 <dd><p>NOTE: This adapter may mutate given <code class="docutils literal notranslate"><span class="pre">input_args_with_path</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5125,7 +5125,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.unflatten.FlatArgsAdapter.get_flat_arg_paths">
-<span class="sig-name descname"><span class="pre">get_flat_arg_paths</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/unflatten.py#L298"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.FlatArgsAdapter.get_flat_arg_paths" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_flat_arg_paths</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/unflatten.py#L298"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.FlatArgsAdapter.get_flat_arg_paths" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a list of paths that are used to access the flat args.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5138,7 +5138,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.unflatten.InterpreterModule">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.unflatten.</span></span><span class="sig-name descname"><span class="pre">InterpreterModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/unflatten.py#L145"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.InterpreterModule" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.unflatten.</span></span><span class="sig-name descname"><span class="pre">InterpreterModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/unflatten.py#L145"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.InterpreterModule" title="Permalink to this definition">#</a></dt>
 <dd><p>A module that uses torch.fx.Interpreter to execute instead of the usual
 codegen that GraphModule uses. This provides better stack trace information
 and makes it easier to debug execution.</p>
@@ -5148,7 +5148,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.unflatten.InterpreterModuleDispatcher">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.unflatten.</span></span><span class="sig-name descname"><span class="pre">InterpreterModuleDispatcher</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attrs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">call_modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/unflatten.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.InterpreterModuleDispatcher" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.unflatten.</span></span><span class="sig-name descname"><span class="pre">InterpreterModuleDispatcher</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attrs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">call_modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/unflatten.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.InterpreterModuleDispatcher" title="Permalink to this definition">#</a></dt>
 <dd><p>A module that carries a sequence of InterpreterModules corresponding to
 a sequence of calls of that module. Each call to the module dispatches
 to the next InterpreterModule, and wraps back around after the last.</p>
@@ -5158,7 +5158,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.unflatten.unflatten">
-<span class="sig-prename descclassname"><span class="pre">torch.export.unflatten.</span></span><span class="sig-name descname"><span class="pre">unflatten</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flat_args_adapter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/unflatten.py#L752"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.unflatten" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.unflatten.</span></span><span class="sig-name descname"><span class="pre">unflatten</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flat_args_adapter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/unflatten.py#L752"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.unflatten.unflatten" title="Permalink to this definition">#</a></dt>
 <dd><p>Unflatten an ExportedProgram, producing a module with the same module
 hierarchy as the original eager module. This can be useful if you are trying
 to use <a class="reference internal" href="#module-torch.export" title="torch.export"><code class="xref py py-mod docutils literal notranslate"><span class="pre">torch.export</span></code></a> with another system that expects a module
@@ -5190,7 +5190,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.register_dataclass">
-<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">register_dataclass</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cls</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">serialized_type_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/__init__.py#L563"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.register_dataclass" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.</span></span><span class="sig-name descname"><span class="pre">register_dataclass</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cls</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">serialized_type_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/__init__.py#L563"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.register_dataclass" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a dataclass as a valid input/output type for <a class="reference internal" href="#torch.export.export" title="torch.export.export"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.export.export()</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5236,7 +5236,7 @@
 
 <span class="target" id="module-torch.export.decomp_utils"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.export.decomp_utils.CustomDecompTable">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.decomp_utils.</span></span><span class="sig-name descname"><span class="pre">CustomDecompTable</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/decomp_utils.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.decomp_utils.</span></span><span class="sig-name descname"><span class="pre">CustomDecompTable</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/decomp_utils.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a custom dictionary that is specifically used for handling decomp_table in export.
 The reason we need this is because in the new world, you can only <em>delete</em> an op from decomp
 table to preserve it. This is problematic for custom ops because we don’t know when the custom
@@ -5254,7 +5254,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.decomp_utils.CustomDecompTable.copy">
-<span class="sig-name descname"><span class="pre">copy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/decomp_utils.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.copy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">copy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/decomp_utils.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.copy" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference internal" href="#torch.export.decomp_utils.CustomDecompTable" title="torch.export.decomp_utils.CustomDecompTable"><em>CustomDecompTable</em></a></p>
@@ -5264,17 +5264,17 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.decomp_utils.CustomDecompTable.items">
-<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/decomp_utils.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.items" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/decomp_utils.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.items" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.decomp_utils.CustomDecompTable.keys">
-<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/decomp_utils.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.keys" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/decomp_utils.py#L70"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.keys" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.decomp_utils.CustomDecompTable.materialize">
-<span class="sig-name descname"><span class="pre">materialize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/decomp_utils.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.materialize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">materialize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/decomp_utils.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.materialize" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)">dict</a>[torch._ops.OperatorBase, <a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><em>Callable</em></a>]</p>
@@ -5284,19 +5284,19 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.decomp_utils.CustomDecompTable.pop">
-<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/decomp_utils.py#L107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/decomp_utils.py#L107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.pop" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.decomp_utils.CustomDecompTable.update">
-<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">other_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/decomp_utils.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.update" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">other_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/decomp_utils.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.decomp_utils.CustomDecompTable.update" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </dd></dl>
 
 <span class="target" id="module-torch.export.experimental"></span><span class="target" id="module-torch.export.passes"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.export.passes.move_to_device_pass">
-<span class="sig-prename descclassname"><span class="pre">torch.export.passes.</span></span><span class="sig-name descname"><span class="pre">move_to_device_pass</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ep</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">location</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/passes/__init__.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.passes.move_to_device_pass" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.passes.</span></span><span class="sig-name descname"><span class="pre">move_to_device_pass</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ep</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">location</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/passes/__init__.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.passes.move_to_device_pass" title="Permalink to this definition">#</a></dt>
 <dd><p>Move the exported program to the given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5325,7 +5325,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveReader.archive_version">
-<span class="sig-name descname"><span class="pre">archive_version</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveReader.archive_version" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">archive_version</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveReader.archive_version" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the archive version.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5336,7 +5336,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveReader.get_file_names">
-<span class="sig-name descname"><span class="pre">get_file_names</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveReader.get_file_names" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_file_names</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveReader.get_file_names" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the file names in the archive.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5347,7 +5347,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveReader.read_bytes">
-<span class="sig-name descname"><span class="pre">read_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveReader.read_bytes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">read_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveReader.read_bytes" title="Permalink to this definition">#</a></dt>
 <dd><p>Read a bytes object from the archive.
 name: The source file inside the archive.</p>
 <dl class="field-list simple">
@@ -5359,7 +5359,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveReader.read_string">
-<span class="sig-name descname"><span class="pre">read_string</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveReader.read_string" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">read_string</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveReader.read_string" title="Permalink to this definition">#</a></dt>
 <dd><p>Read a string object from the archive.
 name: The source file inside the archive.</p>
 <dl class="field-list simple">
@@ -5379,7 +5379,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveWriter.close">
-<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.close" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.close" title="Permalink to this definition">#</a></dt>
 <dd><p>Close the archive.</p>
 <dl class="field-list simple">
 </dl>
@@ -5387,7 +5387,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveWriter.count_prefix">
-<span class="sig-name descname"><span class="pre">count_prefix</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.count_prefix" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">count_prefix</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.count_prefix" title="Permalink to this definition">#</a></dt>
 <dd><p>Count the number of records that start with a given prefix.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5398,7 +5398,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveWriter.has_record">
-<span class="sig-name descname"><span class="pre">has_record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.has_record" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">has_record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.has_record" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if a record exists in the archive.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5409,7 +5409,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveWriter.write_bytes">
-<span class="sig-name descname"><span class="pre">write_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L132"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.write_bytes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">write_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L132"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.write_bytes" title="Permalink to this definition">#</a></dt>
 <dd><p>Write a bytes object to the archive.
 name: The destination file inside the archive.
 data: The bytes object to write.</p>
@@ -5419,7 +5419,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveWriter.write_file">
-<span class="sig-name descname"><span class="pre">write_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.write_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">write_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.write_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy a file into the archive.
 name: The destination file inside the archive.
 file_path: The source file on disk.</p>
@@ -5429,7 +5429,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveWriter.write_folder">
-<span class="sig-name descname"><span class="pre">write_folder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">archive_dir</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">folder_dir</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.write_folder" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">write_folder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">archive_dir</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">folder_dir</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.write_folder" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy a folder into the archive.
 archive_dir: The destination folder inside the archive.
 folder_dir: The source folder on disk.</p>
@@ -5439,7 +5439,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.PT2ArchiveWriter.write_string">
-<span class="sig-name descname"><span class="pre">write_string</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.write_string" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">write_string</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.PT2ArchiveWriter.write_string" title="Permalink to this definition">#</a></dt>
 <dd><p>Write a string object to the archive.
 name: The destination file inside the archive.
 data: The string object to write.</p>
@@ -5451,7 +5451,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.pt2_archive.is_pt2_package">
-<span class="sig-prename descclassname"><span class="pre">torch.export.pt2_archive.</span></span><span class="sig-name descname"><span class="pre">is_pt2_package</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">serialized_model</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/pt2_archive/_package.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.is_pt2_package" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.pt2_archive.</span></span><span class="sig-name descname"><span class="pre">is_pt2_package</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">serialized_model</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/pt2_archive/_package.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.pt2_archive.is_pt2_package" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the serialized model is a PT2 Archive package.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5462,21 +5462,21 @@
 
 <span class="target" id="module-torch.export.pt2_archive.constants"></span><span class="target" id="module-torch.export.exported_program"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.export.exported_program.ModuleCallEntry">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.exported_program.</span></span><span class="sig-name descname"><span class="pre">ModuleCallEntry</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fqn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">signature</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.exported_program.ModuleCallSignature" title="torch.export.exported_program.ModuleCallSignature"><span class="pre">torch.export.exported_program.ModuleCallSignature</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L114"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.exported_program.ModuleCallEntry" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.exported_program.</span></span><span class="sig-name descname"><span class="pre">ModuleCallEntry</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fqn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">signature</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.exported_program.ModuleCallSignature" title="torch.export.exported_program.ModuleCallSignature"><span class="pre">torch.export.exported_program.ModuleCallSignature</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L114"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.exported_program.ModuleCallEntry" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.exported_program.ModuleCallSignature">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.exported_program.</span></span><span class="sig-name descname"><span class="pre">ModuleCallSignature</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.graph_signature.TensorArgument" title="torch.export.graph_signature.TensorArgument"><span class="pre">torch.export.graph_signature.TensorArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymIntArgument" title="torch.export.graph_signature.SymIntArgument"><span class="pre">torch.export.graph_signature.SymIntArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymFloatArgument" title="torch.export.graph_signature.SymFloatArgument"><span class="pre">torch.export.graph_signature.SymFloatArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymBoolArgument" title="torch.export.graph_signature.SymBoolArgument"><span class="pre">torch.export.graph_signature.SymBoolArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.ConstantArgument" title="torch.export.graph_signature.ConstantArgument"><span class="pre">torch.export.graph_signature.ConstantArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.CustomObjArgument" title="torch.export.graph_signature.CustomObjArgument"><span class="pre">torch.export.graph_signature.CustomObjArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.TokenArgument" title="torch.export.graph_signature.TokenArgument"><span class="pre">torch.export.graph_signature.TokenArgument</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">outputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.graph_signature.TensorArgument" title="torch.export.graph_signature.TensorArgument"><span class="pre">torch.export.graph_signature.TensorArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymIntArgument" title="torch.export.graph_signature.SymIntArgument"><span class="pre">torch.export.graph_signature.SymIntArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymFloatArgument" title="torch.export.graph_signature.SymFloatArgument"><span class="pre">torch.export.graph_signature.SymFloatArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymBoolArgument" title="torch.export.graph_signature.SymBoolArgument"><span class="pre">torch.export.graph_signature.SymBoolArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.ConstantArgument" title="torch.export.graph_signature.ConstantArgument"><span class="pre">torch.export.graph_signature.ConstantArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.CustomObjArgument" title="torch.export.graph_signature.CustomObjArgument"><span class="pre">torch.export.graph_signature.CustomObjArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.TokenArgument" title="torch.export.graph_signature.TokenArgument"><span class="pre">torch.export.graph_signature.TokenArgument</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_spec</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.utils._pytree.TreeSpec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_spec</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.utils._pytree.TreeSpec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forward_arg_names</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.exported_program.ModuleCallSignature" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.exported_program.</span></span><span class="sig-name descname"><span class="pre">ModuleCallSignature</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.graph_signature.TensorArgument" title="torch.export.graph_signature.TensorArgument"><span class="pre">torch.export.graph_signature.TensorArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymIntArgument" title="torch.export.graph_signature.SymIntArgument"><span class="pre">torch.export.graph_signature.SymIntArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymFloatArgument" title="torch.export.graph_signature.SymFloatArgument"><span class="pre">torch.export.graph_signature.SymFloatArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymBoolArgument" title="torch.export.graph_signature.SymBoolArgument"><span class="pre">torch.export.graph_signature.SymBoolArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.ConstantArgument" title="torch.export.graph_signature.ConstantArgument"><span class="pre">torch.export.graph_signature.ConstantArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.CustomObjArgument" title="torch.export.graph_signature.CustomObjArgument"><span class="pre">torch.export.graph_signature.CustomObjArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.TokenArgument" title="torch.export.graph_signature.TokenArgument"><span class="pre">torch.export.graph_signature.TokenArgument</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">outputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.graph_signature.TensorArgument" title="torch.export.graph_signature.TensorArgument"><span class="pre">torch.export.graph_signature.TensorArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymIntArgument" title="torch.export.graph_signature.SymIntArgument"><span class="pre">torch.export.graph_signature.SymIntArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymFloatArgument" title="torch.export.graph_signature.SymFloatArgument"><span class="pre">torch.export.graph_signature.SymFloatArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymBoolArgument" title="torch.export.graph_signature.SymBoolArgument"><span class="pre">torch.export.graph_signature.SymBoolArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.ConstantArgument" title="torch.export.graph_signature.ConstantArgument"><span class="pre">torch.export.graph_signature.ConstantArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.CustomObjArgument" title="torch.export.graph_signature.CustomObjArgument"><span class="pre">torch.export.graph_signature.CustomObjArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.TokenArgument" title="torch.export.graph_signature.TokenArgument"><span class="pre">torch.export.graph_signature.TokenArgument</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_spec</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.utils._pytree.TreeSpec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_spec</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.utils._pytree.TreeSpec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forward_arg_names</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.exported_program.ModuleCallSignature" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.export.exported_program.default_decompositions">
-<span class="sig-prename descclassname"><span class="pre">torch.export.exported_program.</span></span><span class="sig-name descname"><span class="pre">default_decompositions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/exported_program.py#L319"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.exported_program.default_decompositions" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.export.exported_program.</span></span><span class="sig-name descname"><span class="pre">default_decompositions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/exported_program.py#L319"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.exported_program.default_decompositions" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the default decomposition table which contains decomposition of
 all ATEN operators to core aten opset. Use this API together with
 <code class="xref py py-func docutils literal notranslate"><span class="pre">run_decompositions()</span></code></p>
@@ -5489,7 +5489,7 @@
 
 <span class="target" id="module-torch.export.custom_ops"></span><span class="target" id="module-torch.export.custom_obj"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.export.custom_obj.ScriptObjectMeta">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.custom_obj.</span></span><span class="sig-name descname"><span class="pre">ScriptObjectMeta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">constant_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">class_fqn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/custom_obj.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.custom_obj.ScriptObjectMeta" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.custom_obj.</span></span><span class="sig-name descname"><span class="pre">ScriptObjectMeta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">constant_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">class_fqn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/custom_obj.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.custom_obj.ScriptObjectMeta" title="Permalink to this definition">#</a></dt>
 <dd><p>Metadata which is stored on nodes representing ScriptObjects.</p>
 <dl class="field-list simple">
 </dl>
@@ -5497,7 +5497,7 @@
 
 <span class="target" id="module-torch.export.graph_signature"></span><dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.ConstantArgument">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">ConstantArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><span class="pre">float</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">NoneType</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ConstantArgument" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">ConstantArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><span class="pre">float</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">NoneType</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ConstantArgument" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5514,7 +5514,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.CustomObjArgument">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">CustomObjArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">class_fqn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">fake_val</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">torch._library.fake_class_registry.FakeScriptObject</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.CustomObjArgument" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">CustomObjArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">class_fqn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">fake_val</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">torch._library.fake_class_registry.FakeScriptObject</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.CustomObjArgument" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5536,7 +5536,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.ExportBackwardSignature">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">ExportBackwardSignature</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">gradients_to_parameters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gradients_to_user_inputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_output</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ExportBackwardSignature" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">ExportBackwardSignature</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">gradients_to_parameters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gradients_to_user_inputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">loss_output</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ExportBackwardSignature" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5558,7 +5558,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.ExportGraphSignature">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">ExportGraphSignature</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_specs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ExportGraphSignature" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">ExportGraphSignature</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_specs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_specs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ExportGraphSignature" title="Permalink to this definition">#</a></dt>
 <dd><p><a class="reference internal" href="#torch.export.graph_signature.ExportGraphSignature" title="torch.export.graph_signature.ExportGraphSignature"><code class="xref py py-class docutils literal notranslate"><span class="pre">ExportGraphSignature</span></code></a> models the input/output signature of Export Graph,
 which is a fx.Graph with stronger invariants guarantees.</p>
 <p>Export Graph is functional and does not access “states” like parameters
@@ -5685,7 +5685,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.graph_signature.ExportGraphSignature.get_replace_hook">
-<span class="sig-name descname"><span class="pre">get_replace_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">replace_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ExportGraphSignature.get_replace_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_replace_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">replace_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ExportGraphSignature.get_replace_hook" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5755,7 +5755,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.export.graph_signature.ExportGraphSignature.replace_all_uses">
-<span class="sig-name descname"><span class="pre">replace_all_uses</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">old</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L515"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ExportGraphSignature.replace_all_uses" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">replace_all_uses</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">old</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L515"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.ExportGraphSignature.replace_all_uses" title="Permalink to this definition">#</a></dt>
 <dd><p>Replace all uses of the old name with new name in the signature.</p>
 <dl class="field-list simple">
 </dl>
@@ -5780,7 +5780,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.InputKind">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">InputKind</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.InputKind" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">InputKind</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.InputKind" title="Permalink to this definition">#</a></dt>
 <dd><p>An enumeration.</p>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.export.graph_signature.InputKind.BUFFER">
@@ -5816,7 +5816,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.InputSpec">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">InputSpec</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kind</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.export.graph_signature.InputKind" title="torch.export.graph_signature.InputKind"><span class="pre">torch.export.graph_signature.InputKind</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.graph_signature.TensorArgument" title="torch.export.graph_signature.TensorArgument"><span class="pre">torch.export.graph_signature.TensorArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymIntArgument" title="torch.export.graph_signature.SymIntArgument"><span class="pre">torch.export.graph_signature.SymIntArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymFloatArgument" title="torch.export.graph_signature.SymFloatArgument"><span class="pre">torch.export.graph_signature.SymFloatArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymBoolArgument" title="torch.export.graph_signature.SymBoolArgument"><span class="pre">torch.export.graph_signature.SymBoolArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.ConstantArgument" title="torch.export.graph_signature.ConstantArgument"><span class="pre">torch.export.graph_signature.ConstantArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.CustomObjArgument" title="torch.export.graph_signature.CustomObjArgument"><span class="pre">torch.export.graph_signature.CustomObjArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.TokenArgument" title="torch.export.graph_signature.TokenArgument"><span class="pre">torch.export.graph_signature.TokenArgument</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.InputSpec" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">InputSpec</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kind</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.export.graph_signature.InputKind" title="torch.export.graph_signature.InputKind"><span class="pre">torch.export.graph_signature.InputKind</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.graph_signature.TensorArgument" title="torch.export.graph_signature.TensorArgument"><span class="pre">torch.export.graph_signature.TensorArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymIntArgument" title="torch.export.graph_signature.SymIntArgument"><span class="pre">torch.export.graph_signature.SymIntArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymFloatArgument" title="torch.export.graph_signature.SymFloatArgument"><span class="pre">torch.export.graph_signature.SymFloatArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymBoolArgument" title="torch.export.graph_signature.SymBoolArgument"><span class="pre">torch.export.graph_signature.SymBoolArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.ConstantArgument" title="torch.export.graph_signature.ConstantArgument"><span class="pre">torch.export.graph_signature.ConstantArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.CustomObjArgument" title="torch.export.graph_signature.CustomObjArgument"><span class="pre">torch.export.graph_signature.CustomObjArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.TokenArgument" title="torch.export.graph_signature.TokenArgument"><span class="pre">torch.export.graph_signature.TokenArgument</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.InputSpec" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5843,7 +5843,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.OutputKind">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">OutputKind</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.OutputKind" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">OutputKind</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.OutputKind" title="Permalink to this definition">#</a></dt>
 <dd><p>An enumeration.</p>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.export.graph_signature.OutputKind.BUFFER_MUTATION">
@@ -5889,7 +5889,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.OutputSpec">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">OutputSpec</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kind</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.export.graph_signature.OutputKind" title="torch.export.graph_signature.OutputKind"><span class="pre">torch.export.graph_signature.OutputKind</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.graph_signature.TensorArgument" title="torch.export.graph_signature.TensorArgument"><span class="pre">torch.export.graph_signature.TensorArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymIntArgument" title="torch.export.graph_signature.SymIntArgument"><span class="pre">torch.export.graph_signature.SymIntArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymFloatArgument" title="torch.export.graph_signature.SymFloatArgument"><span class="pre">torch.export.graph_signature.SymFloatArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymBoolArgument" title="torch.export.graph_signature.SymBoolArgument"><span class="pre">torch.export.graph_signature.SymBoolArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.ConstantArgument" title="torch.export.graph_signature.ConstantArgument"><span class="pre">torch.export.graph_signature.ConstantArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.CustomObjArgument" title="torch.export.graph_signature.CustomObjArgument"><span class="pre">torch.export.graph_signature.CustomObjArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.TokenArgument" title="torch.export.graph_signature.TokenArgument"><span class="pre">torch.export.graph_signature.TokenArgument</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.OutputSpec" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">OutputSpec</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kind</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.export.graph_signature.OutputKind" title="torch.export.graph_signature.OutputKind"><span class="pre">torch.export.graph_signature.OutputKind</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.export.graph_signature.TensorArgument" title="torch.export.graph_signature.TensorArgument"><span class="pre">torch.export.graph_signature.TensorArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymIntArgument" title="torch.export.graph_signature.SymIntArgument"><span class="pre">torch.export.graph_signature.SymIntArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymFloatArgument" title="torch.export.graph_signature.SymFloatArgument"><span class="pre">torch.export.graph_signature.SymFloatArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.SymBoolArgument" title="torch.export.graph_signature.SymBoolArgument"><span class="pre">torch.export.graph_signature.SymBoolArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.ConstantArgument" title="torch.export.graph_signature.ConstantArgument"><span class="pre">torch.export.graph_signature.ConstantArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.CustomObjArgument" title="torch.export.graph_signature.CustomObjArgument"><span class="pre">torch.export.graph_signature.CustomObjArgument</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#torch.export.graph_signature.TokenArgument" title="torch.export.graph_signature.TokenArgument"><span class="pre">torch.export.graph_signature.TokenArgument</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.OutputSpec" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5911,7 +5911,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.SymBoolArgument">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">SymBoolArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.SymBoolArgument" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">SymBoolArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.SymBoolArgument" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5923,7 +5923,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.SymFloatArgument">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">SymFloatArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.SymFloatArgument" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">SymFloatArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.SymFloatArgument" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5935,7 +5935,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.SymIntArgument">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">SymIntArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.SymIntArgument" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">SymIntArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.SymIntArgument" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5947,7 +5947,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.TensorArgument">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">TensorArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.TensorArgument" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">TensorArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.TensorArgument" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5959,7 +5959,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.export.graph_signature.TokenArgument">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">TokenArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/export/graph_signature.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.TokenArgument" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.export.graph_signature.</span></span><span class="sig-name descname"><span class="pre">TokenArgument</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/export/graph_signature.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.export.graph_signature.TokenArgument" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
diff --git a/2.9/export/joint_with_descriptors.html b/2.9/export/joint_with_descriptors.html
index 80efb68af55..b27e53aeeb8 100644
--- a/2.9/export/joint_with_descriptors.html
+++ b/2.9/export/joint_with_descriptors.html
@@ -4411,7 +4411,7 @@ <h1>Joint with descriptors<a class="headerlink" href="#joint-with-descriptors" t
 a distributed SPMD program.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch.aot_autograd.aot_export_joint_with_descriptors">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch.aot_autograd.</span></span><span class="sig-name descname"><span class="pre">aot_export_joint_with_descriptors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stack</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decompositions=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_inference_input_mutations=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_shape_env=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fw_compiler=&lt;function</span> <span class="pre">boxed_nop_preserve_node_meta&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bw_compiler=&lt;function</span> <span class="pre">boxed_nop_preserve_node_meta&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/aot_autograd.py#L1149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch.aot_autograd.aot_export_joint_with_descriptors" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch.aot_autograd.</span></span><span class="sig-name descname"><span class="pre">aot_export_joint_with_descriptors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stack</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decompositions=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_inference_input_mutations=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_shape_env=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fw_compiler=&lt;function</span> <span class="pre">boxed_nop_preserve_node_meta&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bw_compiler=&lt;function</span> <span class="pre">boxed_nop_preserve_node_meta&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/aot_autograd.py#L1149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch.aot_autograd.aot_export_joint_with_descriptors" title="Permalink to this definition">#</a></dt>
 <dd><p>This API captures the joint graph for an nn.Module.  However, unlike
 aot_export_joint_simple or aot_export_module(trace_joint=True), the
 calling convention of the produced joint graph follows no fixed positional
@@ -4473,7 +4473,7 @@ <h1>Joint with descriptors<a class="headerlink" href="#joint-with-descriptors" t
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch.aot_autograd.aot_compile_joint_with_descriptors">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch.aot_autograd.</span></span><span class="sig-name descname"><span class="pre">aot_compile_joint_with_descriptors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">jd</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/aot_autograd.py#L1283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch.aot_autograd.aot_compile_joint_with_descriptors" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch.aot_autograd.</span></span><span class="sig-name descname"><span class="pre">aot_compile_joint_with_descriptors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">jd</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/aot_autograd.py#L1283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch.aot_autograd.aot_compile_joint_with_descriptors" title="Permalink to this definition">#</a></dt>
 <dd><p>Companion function for aot_export_joint_with_descriptors which compiles the joint
 graph into a callable function that follows a standard calling convention.
 params_flat all are arguments.</p>
@@ -4491,13 +4491,13 @@ <h1>Joint with descriptors<a class="headerlink" href="#joint-with-descriptors" t
 <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.AOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">AOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">AOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>Describes where an input from an AOTAutograd produced FX graph comes from</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.AOTInput.is_buffer">
-<span class="sig-name descname"><span class="pre">is_buffer</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTInput.is_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_buffer</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTInput.is_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>True if this input is a buffer or derived from a buffer (e.g., subclass attr)</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4508,7 +4508,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.AOTInput.is_param">
-<span class="sig-name descname"><span class="pre">is_param</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTInput.is_param" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_param</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTInput.is_param" title="Permalink to this definition">#</a></dt>
 <dd><p>True if this input is a parameter or derived from a parameter (e.g., subclass attr)</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4519,7 +4519,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.AOTInput.is_tangent">
-<span class="sig-name descname"><span class="pre">is_tangent</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTInput.is_tangent" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_tangent</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTInput.is_tangent" title="Permalink to this definition">#</a></dt>
 <dd><p>True if this input is a tangent or derived from a tangent (e.g., subclass attr)</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4532,14 +4532,14 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.AOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">AOTOutput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L356"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">AOTOutput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L356"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>Describes where an output from an AOTAutograd produced FX graph will
 eventually be bundled into the final output</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.AOTOutput.is_grad">
-<span class="sig-name descname"><span class="pre">is_grad</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L364"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTOutput.is_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_grad</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L364"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.AOTOutput.is_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>True if this output is a grad or derived from a grad (e.g., subclass attr)</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4552,7 +4552,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.BackwardTokenAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">BackwardTokenAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.BackwardTokenAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">BackwardTokenAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.BackwardTokenAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>The world token which is threaded through side-effectful operations, for backwards</p>
 <dl class="field-list simple">
 </dl>
@@ -4560,7 +4560,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.BackwardTokenAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">BackwardTokenAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L683"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.BackwardTokenAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">BackwardTokenAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L683"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.BackwardTokenAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>The world token output for side-effectful calls, returned so we cannot DCE it, backward only</p>
 <dl class="field-list simple">
 </dl>
@@ -4568,7 +4568,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.BufferAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">BufferAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.BufferAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">BufferAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.BufferAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>The input is a buffer, whose FQN is target</p>
 <dl class="field-list simple">
 </dl>
@@ -4576,7 +4576,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.DummyAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">DummyAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.DummyAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">DummyAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.DummyAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>In some circumstances, we want to call into a function that expects AOTInput, but
 we don’t actually care about that logic (most typically, because some code is being used
 for both compile-time and run-time; AOTInput processing is not needed in this situation.
@@ -4588,7 +4588,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.DummyAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">DummyAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L733"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.DummyAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">DummyAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L733"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.DummyAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>For cases when you don’t actually care about descriptor propagation, do not use under normal
 circumstances.</p>
 <dl class="field-list simple">
@@ -4597,7 +4597,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.GradAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">GradAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">grad_of</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L641"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.GradAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">GradAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">grad_of</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L641"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.GradAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>An output representing the computed gradient for a differentiable input, in the joint graph</p>
 <dl class="field-list simple">
 </dl>
@@ -4605,7 +4605,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.InputMutationAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">InputMutationAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mutated_input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L607"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.InputMutationAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">InputMutationAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mutated_input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L607"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.InputMutationAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>The mutated value of an input tensor, returned so we can appropriately propagate autograd.</p>
 <dl class="field-list simple">
 </dl>
@@ -4613,7 +4613,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.IntermediateBaseAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">IntermediateBaseAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_of</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.IntermediateBaseAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">IntermediateBaseAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_of</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.IntermediateBaseAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>An intermediate base of multiple outputs which alias each other.  We only report ONE of
 the outputs that contributed to this base</p>
 <dl class="field-list simple">
@@ -4622,7 +4622,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.ParamAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">ParamAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L381"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.ParamAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">ParamAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L381"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.ParamAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>The input is a parameter, whose FQN is target</p>
 <dl class="field-list simple">
 </dl>
@@ -4630,7 +4630,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.PhiloxBackwardBaseOffsetAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxBackwardBaseOffsetAOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L541"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxBackwardBaseOffsetAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxBackwardBaseOffsetAOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L541"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxBackwardBaseOffsetAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>The offset for functionalized Philox RNG calls, specifically for backward graph.</p>
 <dl class="field-list simple">
 </dl>
@@ -4638,7 +4638,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.PhiloxBackwardSeedAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxBackwardSeedAOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L533"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxBackwardSeedAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxBackwardSeedAOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L533"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxBackwardSeedAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>The seed for functionalized Philox RNG calls, specifically for backward graph.</p>
 <dl class="field-list simple">
 </dl>
@@ -4646,7 +4646,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.PhiloxForwardBaseOffsetAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxForwardBaseOffsetAOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxForwardBaseOffsetAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxForwardBaseOffsetAOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxForwardBaseOffsetAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>The offset for functionalized Philox RNG calls, specifically for forward graph.</p>
 <dl class="field-list simple">
 </dl>
@@ -4654,7 +4654,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.PhiloxForwardSeedAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxForwardSeedAOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L517"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxForwardSeedAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxForwardSeedAOTInput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L517"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxForwardSeedAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>The seed for functionalized Philox RNG calls, specifically for forward graph.</p>
 <dl class="field-list simple">
 </dl>
@@ -4662,7 +4662,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.PhiloxUpdatedBackwardOffsetAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxUpdatedBackwardOffsetAOTOutput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L665"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxUpdatedBackwardOffsetAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxUpdatedBackwardOffsetAOTOutput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L665"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxUpdatedBackwardOffsetAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>The final offset from the functionalized RNG calls, backward only</p>
 <dl class="field-list simple">
 </dl>
@@ -4670,7 +4670,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.PhiloxUpdatedForwardOffsetAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxUpdatedForwardOffsetAOTOutput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L657"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxUpdatedForwardOffsetAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PhiloxUpdatedForwardOffsetAOTOutput</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L657"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PhiloxUpdatedForwardOffsetAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>The final offset from the functionalized RNG calls, forward only</p>
 <dl class="field-list simple">
 </dl>
@@ -4678,7 +4678,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.PlainAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PlainAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L427"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PlainAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PlainAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L427"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PlainAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>The input is a plain input, corresponding to a particular positional index.</p>
 <p>Note that AOTInput is always relative to a function with a <em>flat</em> calling convention,
 e.g., as accepted by <cite>aot_module_simplified</cite>.  There are some AOTAutograd APIs that
@@ -4690,7 +4690,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.PlainAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PlainAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PlainAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">PlainAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.PlainAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>A plain tensor output at position idx of the output tuple</p>
 <dl class="field-list simple">
 </dl>
@@ -4698,14 +4698,14 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.SavedForBackwardsAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SavedForBackwardsAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L744"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SavedForBackwardsAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SavedForBackwardsAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L744"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SavedForBackwardsAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.SubclassGetAttrAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassGetAttrAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L443"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassGetAttrAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassGetAttrAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L443"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassGetAttrAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>Subclass inputs get unpacked into their constituent pieces before going into an FX
 graph.  This tells you which particular attribute of the subclass this particular
 input corresponds to (of the ‘base’ originally subclass argument.)</p>
@@ -4715,7 +4715,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.SubclassGetAttrAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassGetAttrAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L697"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassGetAttrAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassGetAttrAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L697"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassGetAttrAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>This output will be bundled into a subclass at this location</p>
 <dl class="field-list simple">
 </dl>
@@ -4723,7 +4723,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.SubclassSizeAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassSizeAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L466"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassSizeAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassSizeAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L466"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassSizeAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>Which subclass this particular outer size SymInt input (at dim idx) came from.</p>
 <dl class="field-list simple">
 </dl>
@@ -4731,7 +4731,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.SubclassSizeAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassSizeAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L711"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassSizeAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassSizeAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L711"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassSizeAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>This output size will be bundled into a subclass at this location</p>
 <dl class="field-list simple">
 </dl>
@@ -4739,7 +4739,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.SubclassStrideAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassStrideAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L477"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassStrideAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassStrideAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L477"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassStrideAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>Which subclass this particular outer stride SymInt input (at dim idx) came from.</p>
 <dl class="field-list simple">
 </dl>
@@ -4747,7 +4747,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.SubclassStrideAOTOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassStrideAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L722"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassStrideAOTOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SubclassStrideAOTOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">idx</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L722"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SubclassStrideAOTOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>This output stride will be bundled into a subclass at this location</p>
 <dl class="field-list simple">
 </dl>
@@ -4755,7 +4755,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.SyntheticBaseAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SyntheticBaseAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_of</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L504"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SyntheticBaseAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">SyntheticBaseAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_of</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L504"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.SyntheticBaseAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>This is similar to ViewBaseAOTInput, but this happens when none of the views were differentiable, so
 we weren’t able to get our hands on the true original view and constructed a synthetic one instead
 for the sake of autograd.</p>
@@ -4765,7 +4765,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.descriptors.ViewBaseAOTInput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">ViewBaseAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_of</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/descriptors.py#L488"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.ViewBaseAOTInput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.descriptors.</span></span><span class="sig-name descname"><span class="pre">ViewBaseAOTInput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">base_of</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/descriptors.py#L488"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.descriptors.ViewBaseAOTInput" title="Permalink to this definition">#</a></dt>
 <dd><p>When multiple differentiable inputs are views of the same input, AOTAutograd will replace all of these
 views with a single input representing the base.  If this is undesirable, you can clone the views
 example inputs before passing them into AOTAutograd.</p>
@@ -4783,7 +4783,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 recommend reading :mod:torch._functorch._aot_autograd.descriptors`.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_all_input_and_grad_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_all_input_and_grad_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">g</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_all_input_and_grad_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_all_input_and_grad_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">g</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_all_input_and_grad_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a joint graph with descriptors (meta[‘desc’] on placeholders and
 output), returns the node for every input and its corresponding grad
 output node if it exists.  These tuples are in a dict that is indexed by
@@ -4817,7 +4817,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_all_output_and_tangent_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_all_output_and_tangent_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">g</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L95"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_all_output_and_tangent_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_all_output_and_tangent_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">g</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L95"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_all_output_and_tangent_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Get all output nodes and their corresponding tangent nodes from a joint graph.</p>
 <p>Similar to get_all_input_and_grad_nodes, but returns output nodes paired with
 their tangent nodes (if they exist). This function traverses the graph to find
@@ -4850,7 +4850,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_buffer_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_buffer_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L298"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_buffer_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_buffer_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L298"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_buffer_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Get all buffer nodes from a graph as a list.</p>
 <p>You can rely on this providing the correct order of buffers you need
 to feed into the joint graph (after parameters).</p>
@@ -4876,7 +4876,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_named_buffer_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_named_buffer_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_named_buffer_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_named_buffer_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_named_buffer_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Get buffer nodes mapped by their fully qualified names.</p>
 <p>This function traverses the graph to find all buffer input nodes and
 returns them in a dictionary where keys are the buffer names (FQNs)
@@ -4902,7 +4902,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_named_param_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_named_param_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_named_param_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_named_param_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_named_param_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Get parameter nodes mapped by their fully qualified names.</p>
 <p>This function traverses the graph to find all parameter input nodes and
 returns them in a dictionary where keys are the parameter names (FQNs)
@@ -4928,7 +4928,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_param_and_grad_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_param_and_grad_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L145"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_param_and_grad_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_param_and_grad_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L145"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_param_and_grad_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Get parameter nodes and their corresponding gradient nodes from a joint graph.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4949,7 +4949,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_param_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_param_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L277"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_param_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_param_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L277"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_param_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Get all parameter nodes from a graph as a list.</p>
 <p>You can rely on this providing the correct order of parameters you need
 to feed into the joint graph (at the very beginning of the argument list,
@@ -4976,7 +4976,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_plain_input_and_grad_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_plain_input_and_grad_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_plain_input_and_grad_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_plain_input_and_grad_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_plain_input_and_grad_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Get plain input nodes and their corresponding gradient nodes from a joint graph.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4997,7 +4997,7 @@ <h2>Descriptors<a class="headerlink" href="#descriptors" title="Permalink to thi
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._functorch._aot_autograd.fx_utils.get_plain_output_and_tangent_nodes">
-<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_plain_output_and_tangent_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/_aot_autograd/fx_utils.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_plain_output_and_tangent_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._functorch._aot_autograd.fx_utils.</span></span><span class="sig-name descname"><span class="pre">get_plain_output_and_tangent_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/_aot_autograd/fx_utils.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._functorch._aot_autograd.fx_utils.get_plain_output_and_tangent_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Get plain output nodes and their corresponding tangent nodes from a joint graph.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/fsdp.html b/2.9/fsdp.html
index 0db5e7a8bfa..26f6774df80 100644
--- a/2.9/fsdp.html
+++ b/2.9/fsdp.html
@@ -4396,7 +4396,7 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Feb 02, 2022 | Last Updated On: Jun 11, 2025</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">FullyShardedDataParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sharding_strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cpu_offload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">auto_wrap_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backward_prefetch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">BackwardPrefetch.BACKWARD_PRE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mixed_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignored_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param_init_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sync_module_states</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forward_prefetch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_all_gathers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_orig_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignored_states</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">FullyShardedDataParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sharding_strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cpu_offload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">auto_wrap_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backward_prefetch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">BackwardPrefetch.BACKWARD_PRE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mixed_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignored_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param_init_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sync_module_states</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forward_prefetch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit_all_gathers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_orig_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignored_states</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel" title="Permalink to this definition">#</a></dt>
 <dd><p>A wrapper for sharding module parameters across data parallel workers.</p>
 <p>This is inspired by <a class="reference external" href="https://arxiv.org/abs/2004.13336">Xu et al.</a> as
 well as the ZeRO Stage 3 from <a class="reference external" href="https://www.deepspeed.ai/">DeepSpeed</a>.
@@ -4653,7 +4653,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.apply">
-<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.apply" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every submodule (as returned by <code class="docutils literal notranslate"><span class="pre">.children()</span></code>) as well as self.</p>
 <p>Typical use includes initializing the parameters of a model (see also <a class="reference internal" href="nn.init.html#nn-init-doc"><span class="std std-ref">torch.nn.init</span></a>).</p>
 <p>Compared to <code class="docutils literal notranslate"><span class="pre">torch.nn.Module.apply</span></code>, this version additionally gathers
@@ -4674,7 +4674,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.check_is_root">
-<span class="sig-name descname"><span class="pre">check_is_root</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L543"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.check_is_root" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">check_is_root</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L543"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.check_is_root" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if this instance is a root FSDP module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4685,7 +4685,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.clip_grad_norm_">
-<span class="sig-name descname"><span class="pre">clip_grad_norm_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1063"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.clip_grad_norm_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clip_grad_norm_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1063"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.clip_grad_norm_" title="Permalink to this definition">#</a></dt>
 <dd><p>Clip the gradient norm of all parameters.</p>
 <p>The norm is computed over all parameters’ gradients as viewed as a single vector, and the
 gradients are modified in-place.</p>
@@ -4726,7 +4726,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.flatten_sharded_optim_state_dict">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">flatten_sharded_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sharded_optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1550"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.flatten_sharded_optim_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">flatten_sharded_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sharded_optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1550"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.flatten_sharded_optim_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Flatten a sharded optimizer state-dict.</p>
 <p>The API is similar to <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel.shard_full_optim_state_dict" title="torch.distributed.fsdp.FullyShardedDataParallel.shard_full_optim_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">shard_full_optim_state_dict()</span></code></a>. The only
 difference is that the input <code class="docutils literal notranslate"><span class="pre">sharded_optim_state_dict</span></code> should be
@@ -4754,7 +4754,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L829"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L829"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run the forward pass for the wrapped module, inserting FSDP-specific pre- and post-forward sharding logic.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4765,7 +4765,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.fsdp_modules">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">fsdp_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">root_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L547"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.fsdp_modules" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">fsdp_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">root_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L547"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.fsdp_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return all nested FSDP instances.</p>
 <p>This possibly includes <code class="docutils literal notranslate"><span class="pre">module</span></code> itself and only includes FSDP root modules if <code class="docutils literal notranslate"><span class="pre">root_only=True</span></code>.</p>
 <dl class="field-list simple">
@@ -4789,7 +4789,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.full_optim_state_dict">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">full_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank0_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1361"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.full_optim_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">full_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank0_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1361"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.full_optim_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the full optimizer state-dict.</p>
 <p>Consolidates the full optimizer state on rank 0 and returns it
 as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a> following the convention of
@@ -4842,7 +4842,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.get_state_dict_type">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_state_dict_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L748"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.get_state_dict_type" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_state_dict_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L748"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.get_state_dict_type" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the state_dict_type and the corresponding configurations for the FSDP modules rooted at <code class="docutils literal notranslate"><span class="pre">module</span></code>.</p>
 <p>The target module does not have to be an FSDP module.</p>
 <dl class="field-list simple">
@@ -4870,7 +4870,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.named_buffers">
-<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L968"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.named_buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L968"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.named_buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module buffers, yielding both the name of the buffer and the buffer itself.</p>
 <p>Intercepts buffer names and removes all occurrences of the FSDP-specific flattened buffer prefix
 when inside the <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel.summon_full_params" title="torch.distributed.fsdp.FullyShardedDataParallel.summon_full_params"><code class="xref py py-meth docutils literal notranslate"><span class="pre">summon_full_params()</span></code></a> context manager.</p>
@@ -4883,7 +4883,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.named_parameters">
-<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L986"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.named_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L986"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.named_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module parameters, yielding both the name of the parameter and the parameter itself.</p>
 <p>Intercepts parameter names and removes all occurrences of the FSDP-specific flattened parameter prefix
 when inside the <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel.summon_full_params" title="torch.distributed.fsdp.FullyShardedDataParallel.summon_full_params"><code class="xref py py-meth docutils literal notranslate"><span class="pre">summon_full_params()</span></code></a> context manager.</p>
@@ -4896,7 +4896,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.no_sync">
-<span class="sig-name descname"><span class="pre">no_sync</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1024"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.no_sync" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">no_sync</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1024"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.no_sync" title="Permalink to this definition">#</a></dt>
 <dd><p>Disable gradient synchronizations across FSDP instances.</p>
 <p>Within this context, gradients will be accumulated in module
 variables, which will later be synchronized in the first
@@ -4924,7 +4924,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.optim_state_dict">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1798"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.optim_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1798"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.optim_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform the state-dict of an optimizer corresponding to a sharded model.</p>
 <p>The given state-dict can be transformed to one of three types:
 1) full optimizer state_dict, 2) sharded optimizer state_dict, 3) local optimizer state_dict.</p>
@@ -4998,7 +4998,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.optim_state_dict_to_load">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">optim_state_dict_to_load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_named_optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">load_directly</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1894"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.optim_state_dict_to_load" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">optim_state_dict_to_load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_named_optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">load_directly</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1894"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.optim_state_dict_to_load" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert an optimizer state-dict so that it can be loaded into the optimizer associated with the FSDP model.</p>
 <p>Given a <code class="docutils literal notranslate"><span class="pre">optim_state_dict</span></code> that is transformed through
 <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel.optim_state_dict" title="torch.distributed.fsdp.FullyShardedDataParallel.optim_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">optim_state_dict()</span></code></a>, it gets converted to the flattened optimizer
@@ -5069,7 +5069,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.register_comm_hook">
-<span class="sig-name descname"><span class="pre">register_comm_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1984"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.register_comm_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_comm_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1984"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.register_comm_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a communication hook.</p>
 <p>This is an enhancement that provides a flexible hook to users where they can specify how FSDP aggregates
 gradients across multiple workers.
@@ -5115,7 +5115,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.rekey_optim_state_dict">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">rekey_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_key_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1673"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.rekey_optim_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">rekey_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_key_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1673"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.rekey_optim_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Re-keys the optimizer state dict <code class="docutils literal notranslate"><span class="pre">optim_state_dict</span></code> to use the key type <code class="docutils literal notranslate"><span class="pre">optim_state_key_type</span></code>.</p>
 <p>This can be used to achieve compatibility between optimizer state dicts from models with FSDP
 instances and ones without.</p>
@@ -5152,7 +5152,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.scatter_full_optim_state_dict">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">scatter_full_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">full_optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.scatter_full_optim_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">scatter_full_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">full_optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.scatter_full_optim_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Scatter the full optimizer state dict from rank 0 to all other ranks.</p>
 <p>Returns the sharded optimizer state dict on each rank.
 The return value is the same as <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel.shard_full_optim_state_dict" title="torch.distributed.fsdp.FullyShardedDataParallel.shard_full_optim_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">shard_full_optim_state_dict()</span></code></a>, and on rank
@@ -5217,7 +5217,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.set_state_dict_type">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_state_dict_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.set_state_dict_type" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_state_dict_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.set_state_dict_type" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the <code class="docutils literal notranslate"><span class="pre">state_dict_type</span></code> of all the descendant FSDP modules of the target module.</p>
 <p>Also takes (optional) configuration for the model’s and optimizer’s state dict.
 The target module does not have to be a FSDP module. If the target
@@ -5271,7 +5271,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.shard_full_optim_state_dict">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">shard_full_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">full_optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1471"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.shard_full_optim_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">shard_full_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">full_optim_state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1471"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.shard_full_optim_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Shard a full optimizer state-dict.</p>
 <p>Remaps the state in <code class="docutils literal notranslate"><span class="pre">full_optim_state_dict</span></code> to flattened parameters instead of unflattened
 parameters and restricts to only this rank’s part of the optimizer state.
@@ -5334,7 +5334,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.sharded_optim_state_dict">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">sharded_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.sharded_optim_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">sharded_optim_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L1437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.sharded_optim_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the optimizer state-dict in its sharded form.</p>
 <p>The API is similar to <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel.full_optim_state_dict" title="torch.distributed.fsdp.FullyShardedDataParallel.full_optim_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">full_optim_state_dict()</span></code></a> but this API chunks
 all non-zero-dimension states to <code class="xref py py-class docutils literal notranslate"><span class="pre">ShardedTensor</span></code> to save memory.
@@ -5355,7 +5355,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.state_dict_type">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">state_dict_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L784"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.state_dict_type" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">state_dict_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L784"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.state_dict_type" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the <code class="docutils literal notranslate"><span class="pre">state_dict_type</span></code> of all the descendant FSDP modules of the target module.</p>
 <p>This context manager has the same functions as <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel.set_state_dict_type" title="torch.distributed.fsdp.FullyShardedDataParallel.set_state_dict_type"><code class="xref py py-meth docutils literal notranslate"><span class="pre">set_state_dict_type()</span></code></a>. Read the document of
 <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel.set_state_dict_type" title="torch.distributed.fsdp.FullyShardedDataParallel.set_state_dict_type"><code class="xref py py-meth docutils literal notranslate"><span class="pre">set_state_dict_type()</span></code></a> for the detail.</p>
@@ -5387,7 +5387,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullyShardedDataParallel.summon_full_params">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">summon_full_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">writeback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank0_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/fully_sharded_data_parallel.py#L856"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.summon_full_params" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">summon_full_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">writeback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank0_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/fully_sharded_data_parallel.py#L856"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullyShardedDataParallel.summon_full_params" title="Permalink to this definition">#</a></dt>
 <dd><p>Expose full params for FSDP instances with this context manager.</p>
 <p>Can be useful <em>after</em> forward/backward for a model to get
 the params for additional processing or checking. It can take a non-FSDP
@@ -5477,7 +5477,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.BackwardPrefetch">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">BackwardPrefetch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.BackwardPrefetch" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">BackwardPrefetch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.BackwardPrefetch" title="Permalink to this definition">#</a></dt>
 <dd><p>This configures explicit backward prefetching, which improves throughput by
 enabling communication and computation overlap in the backward pass at the
 cost of slightly increased memory usage.</p>
@@ -5509,7 +5509,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.ShardingStrategy">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">ShardingStrategy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.ShardingStrategy" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">ShardingStrategy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.ShardingStrategy" title="Permalink to this definition">#</a></dt>
 <dd><p>This specifies the sharding strategy to be used for distributed training by
 <a class="reference internal" href="#torch.distributed.fsdp.FullyShardedDataParallel" title="torch.distributed.fsdp.FullyShardedDataParallel"><code class="xref py py-class docutils literal notranslate"><span class="pre">FullyShardedDataParallel</span></code></a>.</p>
 <ul class="simple">
@@ -5544,7 +5544,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.MixedPrecision">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">MixedPrecision</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_dtype=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_dtype=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffer_dtype=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_low_precision_grads=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_forward_inputs=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_root_forward_inputs=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_module_classes_to_ignore=(&lt;class</span> <span class="pre">'torch.nn.modules.batchnorm._BatchNorm'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">)</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.MixedPrecision" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">MixedPrecision</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_dtype=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_dtype=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffer_dtype=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_low_precision_grads=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_forward_inputs=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_root_forward_inputs=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_module_classes_to_ignore=(&lt;class</span> <span class="pre">'torch.nn.modules.batchnorm._BatchNorm'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">)</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.MixedPrecision" title="Permalink to this definition">#</a></dt>
 <dd><p>This configures FSDP-native mixed precision training.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Variables</dt>
@@ -5668,7 +5668,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.CPUOffload">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">CPUOffload</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L230"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.CPUOffload" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">CPUOffload</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L230"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.CPUOffload" title="Permalink to this definition">#</a></dt>
 <dd><p>This configures CPU offloading.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Variables</dt>
@@ -5682,7 +5682,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.StateDictConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">StateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L276"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.StateDictConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">StateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L276"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.StateDictConfig" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">StateDictConfig</span></code> is the base class for all <code class="docutils literal notranslate"><span class="pre">state_dict</span></code> configuration
 classes. Users should instantiate a child class (e.g.
 <code class="docutils literal notranslate"><span class="pre">FullStateDictConfig</span></code>) in order to configure settings for the
@@ -5698,7 +5698,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullStateDictConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">FullStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank0_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L293"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullStateDictConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">FullStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank0_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L293"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullStateDictConfig" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">FullStateDictConfig</span></code> is a config class meant to be used with
 <code class="docutils literal notranslate"><span class="pre">StateDictType.FULL_STATE_DICT</span></code>. We recommend enabling both
 <code class="docutils literal notranslate"><span class="pre">offload_to_cpu=True</span></code> and <code class="docutils literal notranslate"><span class="pre">rank0_only=True</span></code> when saving full state
@@ -5739,7 +5739,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.ShardedStateDictConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">ShardedStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_use_dtensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.ShardedStateDictConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">ShardedStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_use_dtensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.ShardedStateDictConfig" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">ShardedStateDictConfig</span></code> is a config class meant to be used with
 <code class="docutils literal notranslate"><span class="pre">StateDictType.SHARDED_STATE_DICT</span></code>.</p>
 <dl class="field-list simple">
@@ -5759,14 +5759,14 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.LocalStateDictConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">LocalStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L335"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.LocalStateDictConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">LocalStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L335"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.LocalStateDictConfig" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.OptimStateDictConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">OptimStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L359"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.OptimStateDictConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">OptimStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L359"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.OptimStateDictConfig" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">OptimStateDictConfig</span></code> is the base class for all <code class="docutils literal notranslate"><span class="pre">optim_state_dict</span></code>
 configuration classes.  Users should instantiate a child class (e.g.
 <code class="docutils literal notranslate"><span class="pre">FullOptimStateDictConfig</span></code>) in order to configure settings for the
@@ -5783,7 +5783,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.FullOptimStateDictConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">FullOptimStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank0_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullOptimStateDictConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">FullOptimStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank0_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.FullOptimStateDictConfig" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Variables</dt>
 <dd class="field-odd"><p><strong>rank0_only</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><em>bool</em></a>) – If <code class="docutils literal notranslate"><span class="pre">True</span></code>, then only rank 0 saves the full state
@@ -5795,7 +5795,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.ShardedOptimStateDictConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">ShardedOptimStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_use_dtensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L394"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.ShardedOptimStateDictConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">ShardedOptimStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_use_dtensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L394"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.ShardedOptimStateDictConfig" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">ShardedOptimStateDictConfig</span></code> is a config class meant to be used with
 <code class="docutils literal notranslate"><span class="pre">StateDictType.SHARDED_STATE_DICT</span></code>.</p>
 <dl class="field-list simple">
@@ -5815,14 +5815,14 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.LocalOptimStateDictConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">LocalOptimStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.LocalOptimStateDictConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">LocalOptimStateDictConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">offload_to_cpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.LocalOptimStateDictConfig" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.fsdp.StateDictSettings">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">StateDictSettings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict_type</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.distributed.fsdp.api.StateDictType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.distributed.fsdp.StateDictConfig" title="torch.distributed.fsdp.api.StateDictConfig"><span class="pre">torch.distributed.fsdp.api.StateDictConfig</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.distributed.fsdp.OptimStateDictConfig" title="torch.distributed.fsdp.api.OptimStateDictConfig"><span class="pre">torch.distributed.fsdp.api.OptimStateDictConfig</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/fsdp/api.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.StateDictSettings" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.fsdp.</span></span><span class="sig-name descname"><span class="pre">StateDictSettings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict_type</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.distributed.fsdp.api.StateDictType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_dict_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.distributed.fsdp.StateDictConfig" title="torch.distributed.fsdp.api.StateDictConfig"><span class="pre">torch.distributed.fsdp.api.StateDictConfig</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">optim_state_dict_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#torch.distributed.fsdp.OptimStateDictConfig" title="torch.distributed.fsdp.api.OptimStateDictConfig"><span class="pre">torch.distributed.fsdp.api.OptimStateDictConfig</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/fsdp/api.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.fsdp.StateDictSettings" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
diff --git a/2.9/future_mod.html b/2.9/future_mod.html
index 4c8bf99a035..3a08e9d3855 100644
--- a/2.9/future_mod.html
+++ b/2.9/future_mod.html
@@ -4396,7 +4396,7 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Feb 05, 2024 | Last Updated On: Jun 12, 2025</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.__future__.set_overwrite_module_params_on_conversion">
-<span class="sig-prename descclassname"><span class="pre">torch.__future__.</span></span><span class="sig-name descname"><span class="pre">set_overwrite_module_params_on_conversion</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__future__.py#L5"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__future__.set_overwrite_module_params_on_conversion" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.__future__.</span></span><span class="sig-name descname"><span class="pre">set_overwrite_module_params_on_conversion</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__future__.py#L5"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__future__.set_overwrite_module_params_on_conversion" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether to assign new tensors to the parameters instead of changing the
 existing parameters in-place when converting an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code>.</p>
 <p>When enabled, the following methods will assign new parameters to the module:</p>
@@ -4415,7 +4415,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.__future__.get_overwrite_module_params_on_conversion">
-<span class="sig-prename descclassname"><span class="pre">torch.__future__.</span></span><span class="sig-name descname"><span class="pre">get_overwrite_module_params_on_conversion</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__future__.py#L25"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__future__.get_overwrite_module_params_on_conversion" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.__future__.</span></span><span class="sig-name descname"><span class="pre">get_overwrite_module_params_on_conversion</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__future__.py#L25"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__future__.get_overwrite_module_params_on_conversion" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether to assign new tensors to the parameters instead of changing the
 existing parameters in-place when converting an <a class="reference internal" href="generated/torch.nn.Module.html#torch.nn.Module" title="torch.nn.Module"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Module</span></code></a>. Defaults to <code class="docutils literal notranslate"><span class="pre">False</span></code>.</p>
 <p>See <a class="reference internal" href="#torch.__future__.set_overwrite_module_params_on_conversion" title="torch.__future__.set_overwrite_module_params_on_conversion"><code class="xref py py-func docutils literal notranslate"><span class="pre">set_overwrite_module_params_on_conversion()</span></code></a> for more information.</p>
@@ -4428,7 +4428,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.__future__.set_swap_module_params_on_conversion">
-<span class="sig-prename descclassname"><span class="pre">torch.__future__.</span></span><span class="sig-name descname"><span class="pre">set_swap_module_params_on_conversion</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__future__.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__future__.set_swap_module_params_on_conversion" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.__future__.</span></span><span class="sig-name descname"><span class="pre">set_swap_module_params_on_conversion</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__future__.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__future__.set_swap_module_params_on_conversion" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether to use <a class="reference internal" href="generated/torch.utils.swap_tensors.html#torch.utils.swap_tensors" title="torch.utils.swap_tensors"><code class="xref py py-func docutils literal notranslate"><span class="pre">swap_tensors()</span></code></a> instead of setting <code class="docutils literal notranslate"><span class="pre">.data</span></code> to
 change the existing parameters in-place when converting an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> and instead
 of <code class="docutils literal notranslate"><span class="pre">param.copy_(state_dict[key])</span></code> when loading a state dict into an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code>.</p>
@@ -4461,7 +4461,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.__future__.get_swap_module_params_on_conversion">
-<span class="sig-prename descclassname"><span class="pre">torch.__future__.</span></span><span class="sig-name descname"><span class="pre">get_swap_module_params_on_conversion</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__future__.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__future__.get_swap_module_params_on_conversion" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.__future__.</span></span><span class="sig-name descname"><span class="pre">get_swap_module_params_on_conversion</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__future__.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.__future__.get_swap_module_params_on_conversion" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether to use <a class="reference internal" href="generated/torch.utils.swap_tensors.html#torch.utils.swap_tensors" title="torch.utils.swap_tensors"><code class="xref py py-func docutils literal notranslate"><span class="pre">swap_tensors()</span></code></a> instead of setting .data to
 change the existing parameters in-place when converting an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code>. Defaults to <code class="docutils literal notranslate"><span class="pre">False</span></code>.</p>
 <p>See <a class="reference internal" href="#torch.__future__.set_swap_module_params_on_conversion" title="torch.__future__.set_swap_module_params_on_conversion"><code class="xref py py-func docutils literal notranslate"><span class="pre">set_swap_module_params_on_conversion()</span></code></a> for more information.</p>
diff --git a/2.9/futures.html b/2.9/futures.html
index 37376ecacff..a45093c9e81 100644
--- a/2.9/futures.html
+++ b/2.9/futures.html
@@ -4413,7 +4413,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.futures.Future.add_done_callback">
-<span class="sig-name descname"><span class="pre">add_done_callback</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.add_done_callback" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_done_callback</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.add_done_callback" title="Permalink to this definition">#</a></dt>
 <dd><p>Append the given callback function to this <code class="docutils literal notranslate"><span class="pre">Future</span></code>, which will be run
 when the <code class="docutils literal notranslate"><span class="pre">Future</span></code> is completed.  Multiple callbacks can be added to
 the same <code class="docutils literal notranslate"><span class="pre">Future</span></code>, but the order in which they will be executed cannot
@@ -4459,7 +4459,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.futures.Future.done">
-<span class="sig-name descname"><span class="pre">done</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.done" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">done</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.done" title="Permalink to this definition">#</a></dt>
 <dd><p>Return <code class="docutils literal notranslate"><span class="pre">True</span></code> if this <code class="docutils literal notranslate"><span class="pre">Future</span></code> is done. A <code class="docutils literal notranslate"><span class="pre">Future</span></code> is done if it
 has a result or an exception.</p>
 <p>If the value contains tensors that reside on GPUs, <code class="docutils literal notranslate"><span class="pre">Future.done()</span></code>
@@ -4476,7 +4476,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.futures.Future.set_exception">
-<span class="sig-name descname"><span class="pre">set_exception</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">result</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L250"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.set_exception" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_exception</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">result</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L250"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.set_exception" title="Permalink to this definition">#</a></dt>
 <dd><p>Set an exception for this <code class="docutils literal notranslate"><span class="pre">Future</span></code>, which will mark this <code class="docutils literal notranslate"><span class="pre">Future</span></code> as
 completed with an error and trigger all attached callbacks. Note that
 when calling wait()/value() on this <code class="docutils literal notranslate"><span class="pre">Future</span></code>, the exception set here
@@ -4499,7 +4499,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.futures.Future.set_result">
-<span class="sig-name descname"><span class="pre">set_result</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">result</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L210"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.set_result" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_result</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">result</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L210"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.set_result" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the result for this <code class="docutils literal notranslate"><span class="pre">Future</span></code>, which will mark this <code class="docutils literal notranslate"><span class="pre">Future</span></code> as
 completed and trigger all attached callbacks. Note that a <code class="docutils literal notranslate"><span class="pre">Future</span></code>
 cannot be marked completed twice.</p>
@@ -4539,7 +4539,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.futures.Future.then">
-<span class="sig-name descname"><span class="pre">then</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.then" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">then</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.then" title="Permalink to this definition">#</a></dt>
 <dd><p>Append the given callback function to this <code class="docutils literal notranslate"><span class="pre">Future</span></code>, which will be run
 when the <code class="docutils literal notranslate"><span class="pre">Future</span></code> is completed.  Multiple callbacks can be added to
 the same <code class="docutils literal notranslate"><span class="pre">Future</span></code>, but the order in which they will be executed cannot
@@ -4608,7 +4608,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.futures.Future.value">
-<span class="sig-name descname"><span class="pre">value</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.value" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">value</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L79"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.value" title="Permalink to this definition">#</a></dt>
 <dd><p>Obtain the value of an already-completed future.</p>
 <p>This method should only be called after a call to <a class="reference internal" href="#torch.futures.Future.wait" title="torch.futures.Future.wait"><code class="xref py py-meth docutils literal notranslate"><span class="pre">wait()</span></code></a> has
 completed, or inside a callback function passed to <a class="reference internal" href="#torch.futures.Future.then" title="torch.futures.Future.then"><code class="xref py py-meth docutils literal notranslate"><span class="pre">then()</span></code></a>. In
@@ -4632,7 +4632,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.futures.Future.wait">
-<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.wait" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.Future.wait" title="Permalink to this definition">#</a></dt>
 <dd><p>Block until the value of this <code class="docutils literal notranslate"><span class="pre">Future</span></code> is ready.</p>
 <p>If the value contains tensors that reside on GPUs, then an additional
 synchronization is performed with the kernels (executing on the device)
@@ -4659,7 +4659,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.futures.collect_all">
-<span class="sig-prename descclassname"><span class="pre">torch.futures.</span></span><span class="sig-name descname"><span class="pre">collect_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">futures</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.collect_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.futures.</span></span><span class="sig-name descname"><span class="pre">collect_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">futures</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.collect_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Collects the provided <a class="reference internal" href="#torch.futures.Future" title="torch.futures.Future"><code class="xref py py-class docutils literal notranslate"><span class="pre">Future</span></code></a> objects into a single
 combined <a class="reference internal" href="#torch.futures.Future" title="torch.futures.Future"><code class="xref py py-class docutils literal notranslate"><span class="pre">Future</span></code></a> that is completed when all of the
 sub-futures are completed.</p>
@@ -4694,7 +4694,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.futures.wait_all">
-<span class="sig-prename descclassname"><span class="pre">torch.futures.</span></span><span class="sig-name descname"><span class="pre">wait_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">futures</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/futures/__init__.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.wait_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.futures.</span></span><span class="sig-name descname"><span class="pre">wait_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">futures</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/futures/__init__.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.futures.wait_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Waits for all provided futures to be complete, and returns
 the list of completed values. If any of the futures encounters an error,
 the method will exit early and report the error not waiting for other
diff --git a/2.9/fx.html b/2.9/fx.html
index d88de35d514..908d974e5ff 100644
--- a/2.9/fx.html
+++ b/2.9/fx.html
@@ -5534,7 +5534,7 @@ <h3>Miscellanea<a class="headerlink" href="#miscellanea" title="Permalink to thi
 <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.symbolic_trace">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">symbolic_trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concrete_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L1287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.symbolic_trace" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">symbolic_trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concrete_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L1287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.symbolic_trace" title="Permalink to this definition">#</a></dt>
 <dd><p>Symbolic tracing API</p>
 <p>Given an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> or function instance <code class="docutils literal notranslate"><span class="pre">root</span></code>, this function will return a <code class="docutils literal notranslate"><span class="pre">GraphModule</span></code>
 constructed by recording operations seen while tracing through <code class="docutils literal notranslate"><span class="pre">root</span></code>.</p>
@@ -5595,7 +5595,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.wrap">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">wrap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn_or_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L1223"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.wrap" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">wrap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn_or_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L1223"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.wrap" title="Permalink to this definition">#</a></dt>
 <dd><p>This function can be called at module-level scope to register fn_or_name as a “leaf function”.
 A “leaf function” will be preserved as a CallFunction node in the FX trace instead of being
 traced through:</p>
@@ -5637,7 +5637,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.GraphModule">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">GraphModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph_module.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">GraphModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph_module.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule" title="Permalink to this definition">#</a></dt>
 <dd><p>GraphModule is an nn.Module generated from an fx.Graph. Graphmodule has a
 <code class="docutils literal notranslate"><span class="pre">graph</span></code> attribute, as well as <code class="docutils literal notranslate"><span class="pre">code</span></code> and <code class="docutils literal notranslate"><span class="pre">forward</span></code> attributes generated
 from that <code class="docutils literal notranslate"><span class="pre">graph</span></code>.</p>
@@ -5654,7 +5654,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.GraphModule.__init__">
-<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">class_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'GraphModule'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph_module.py#L450"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.__init__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">class_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'GraphModule'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph_module.py#L450"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.__init__" title="Permalink to this definition">#</a></dt>
 <dd><p>Construct a GraphModule.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5681,7 +5681,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.GraphModule.add_submodule">
-<span class="sig-name descname"><span class="pre">add_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">m</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph_module.py#L658"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.add_submodule" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">m</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph_module.py#L658"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.add_submodule" title="Permalink to this definition">#</a></dt>
 <dd><p>Adds the given submodule to <code class="docutils literal notranslate"><span class="pre">self</span></code>.</p>
 <p>This installs empty Modules where none exist yet if they are
 subpaths of <code class="docutils literal notranslate"><span class="pre">target</span></code>.</p>
@@ -5724,7 +5724,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.GraphModule.delete_all_unused_submodules">
-<span class="sig-name descname"><span class="pre">delete_all_unused_submodules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph_module.py#L740"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.delete_all_unused_submodules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">delete_all_unused_submodules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph_module.py#L740"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.delete_all_unused_submodules" title="Permalink to this definition">#</a></dt>
 <dd><p>Deletes all unused submodules from <code class="docutils literal notranslate"><span class="pre">self</span></code>.</p>
 <p>A Module is considered “used” if any one of the following is
 true:
@@ -5744,7 +5744,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.GraphModule.delete_submodule">
-<span class="sig-name descname"><span class="pre">delete_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph_module.py#L698"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.delete_submodule" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">delete_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph_module.py#L698"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.delete_submodule" title="Permalink to this definition">#</a></dt>
 <dd><p>Deletes the given submodule from <code class="docutils literal notranslate"><span class="pre">self</span></code>.</p>
 <p>The module will not be deleted if <code class="docutils literal notranslate"><span class="pre">target</span></code> is not a valid
 target.</p>
@@ -5781,7 +5781,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.GraphModule.print_readable">
-<span class="sig-name descname"><span class="pre">print_readable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">print_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">colored</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fast_sympy_print</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expanded_def</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph_module.py#L929"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.print_readable" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">print_readable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">print_output</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">colored</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fast_sympy_print</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expanded_def</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph_module.py#L929"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.print_readable" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the Python code generated for current GraphModule and its children GraphModules</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -5793,7 +5793,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.GraphModule.recompile">
-<span class="sig-name descname"><span class="pre">recompile</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph_module.py#L807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.recompile" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">recompile</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph_module.py#L807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.recompile" title="Permalink to this definition">#</a></dt>
 <dd><p>Recompile this GraphModule from its <code class="docutils literal notranslate"><span class="pre">graph</span></code> attribute. This should be
 called after editing the contained <code class="docutils literal notranslate"><span class="pre">graph</span></code>, otherwise the generated
 code of this <code class="docutils literal notranslate"><span class="pre">GraphModule</span></code> will be out of date.</p>
@@ -5810,7 +5810,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.GraphModule.to_folder">
-<span class="sig-name descname"><span class="pre">to_folder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">folder</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'FxModule'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph_module.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.to_folder" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_folder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">folder</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'FxModule'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph_module.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.GraphModule.to_folder" title="Permalink to this definition">#</a></dt>
 <dd><dl>
 <dt>Dumps out module to <code class="docutils literal notranslate"><span class="pre">folder</span></code> with <code class="docutils literal notranslate"><span class="pre">module_name</span></code> so that it can be</dt><dd><p>imported with <code class="docutils literal notranslate"><span class="pre">from</span> <span class="pre">&lt;folder&gt;</span> <span class="pre">import</span> <span class="pre">&lt;module_name&gt;</span></code></p>
 <p>Args:</p>
@@ -5835,7 +5835,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.Graph">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">owning_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer_cls</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer_extras</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L996"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">owning_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer_cls</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer_extras</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L996"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">Graph</span></code> is the main data structure used in the FX Intermediate Representation.
 It consists of a series of <code class="docutils literal notranslate"><span class="pre">Node</span></code> s, each representing callsites (or other
 syntactic constructs). The list of <code class="docutils literal notranslate"><span class="pre">Node</span></code> s, taken together, constitute a
@@ -5884,7 +5884,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.__init__">
-<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">owning_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer_cls</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer_extras</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1045"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.__init__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">owning_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer_cls</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer_extras</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1045"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.__init__" title="Permalink to this definition">#</a></dt>
 <dd><p>Construct an empty Graph.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -5896,7 +5896,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.call_function">
-<span class="sig-name descname"><span class="pre">call_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">the_function</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1524"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.call_function" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">the_function</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1524"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.call_function" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert a <code class="docutils literal notranslate"><span class="pre">call_function</span></code> <code class="docutils literal notranslate"><span class="pre">Node</span></code> into the <code class="docutils literal notranslate"><span class="pre">Graph</span></code>. A <code class="docutils literal notranslate"><span class="pre">call_function</span></code> node
 represents a call to a Python callable, specified by <code class="docutils literal notranslate"><span class="pre">the_function</span></code>.</p>
 <dl class="field-list simple">
@@ -5934,7 +5934,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.call_method">
-<span class="sig-name descname"><span class="pre">call_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">method_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1485"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.call_method" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">method_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1485"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.call_method" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert a <code class="docutils literal notranslate"><span class="pre">call_method</span></code> <code class="docutils literal notranslate"><span class="pre">Node</span></code> into the <code class="docutils literal notranslate"><span class="pre">Graph</span></code>. A <code class="docutils literal notranslate"><span class="pre">call_method</span></code> node
 represents a call to a given method on the 0th element of <code class="docutils literal notranslate"><span class="pre">args</span></code>.</p>
 <dl class="field-list simple">
@@ -5971,7 +5971,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.call_module">
-<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1435"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.call_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1435"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.call_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert a <code class="docutils literal notranslate"><span class="pre">call_module</span></code> <code class="docutils literal notranslate"><span class="pre">Node</span></code> into the <code class="docutils literal notranslate"><span class="pre">Graph</span></code>. A <code class="docutils literal notranslate"><span class="pre">call_module</span></code> node
 represents a call to the forward() function of a <code class="docutils literal notranslate"><span class="pre">Module</span></code> in the <code class="docutils literal notranslate"><span class="pre">Module</span></code>
 hierarchy.</p>
@@ -6011,7 +6011,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.create_node">
-<span class="sig-name descname"><span class="pre">create_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.create_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.create_node" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="docutils literal notranslate"><span class="pre">Node</span></code> and add it to the <code class="docutils literal notranslate"><span class="pre">Graph</span></code> at the current insert-point.
 Note that the current insert-point can be set via <a class="reference internal" href="#torch.fx.Graph.inserting_before" title="torch.fx.Graph.inserting_before"><code class="xref py py-meth docutils literal notranslate"><span class="pre">Graph.inserting_before()</span></code></a>
 and <a class="reference internal" href="#torch.fx.Graph.inserting_after" title="torch.fx.Graph.inserting_after"><code class="xref py py-meth docutils literal notranslate"><span class="pre">Graph.inserting_after()</span></code></a>.</p>
@@ -6045,7 +6045,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.eliminate_dead_code">
-<span class="sig-name descname"><span class="pre">eliminate_dead_code</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">is_impure_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1855"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.eliminate_dead_code" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">eliminate_dead_code</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">is_impure_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1855"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.eliminate_dead_code" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove all dead code from the graph, based on each node’s number of
 users, and whether the nodes have any side effects. The graph must be
 topologically sorted before calling.</p>
@@ -6096,7 +6096,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.erase_node">
-<span class="sig-name descname"><span class="pre">erase_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to_erase</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1246"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.erase_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">erase_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to_erase</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1246"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.erase_node" title="Permalink to this definition">#</a></dt>
 <dd><p>Erases a <code class="docutils literal notranslate"><span class="pre">Node</span></code> from the <code class="docutils literal notranslate"><span class="pre">Graph</span></code>. Throws an exception if
 there are still users of that node in the <code class="docutils literal notranslate"><span class="pre">Graph</span></code>.</p>
 <dl class="field-list simple">
@@ -6112,7 +6112,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.find_nodes">
-<span class="sig-name descname"><span class="pre">find_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sort</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1096"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.find_nodes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">find_nodes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sort</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1096"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.find_nodes" title="Permalink to this definition">#</a></dt>
 <dd><p>Allows for fast query of nodes</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -6136,7 +6136,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.get_attr">
-<span class="sig-name descname"><span class="pre">get_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qualified_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1367"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.get_attr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qualified_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1367"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.get_attr" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert a <code class="docutils literal notranslate"><span class="pre">get_attr</span></code> node into the Graph. A <code class="docutils literal notranslate"><span class="pre">get_attr</span></code> <code class="docutils literal notranslate"><span class="pre">Node</span></code> represents the
 fetch of an attribute from the <code class="docutils literal notranslate"><span class="pre">Module</span></code> hierarchy.</p>
 <dl class="field-list simple">
@@ -6170,7 +6170,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.graph_copy">
-<span class="sig-name descname"><span class="pre">graph_copy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">g</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_map</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_output_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.graph_copy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">graph_copy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">g</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val_map</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_output_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.graph_copy" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy all nodes from a given graph into <code class="docutils literal notranslate"><span class="pre">self</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -6197,7 +6197,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.inserting_after">
-<span class="sig-name descname"><span class="pre">inserting_after</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1310"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.inserting_after" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">inserting_after</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1310"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.inserting_after" title="Permalink to this definition">#</a></dt>
 <dd><dl>
 <dt>Set the point at which create_node and companion methods will insert into the graph.</dt><dd><p>When used within a ‘with’ statement, this will temporary set the insert point and
 then restore it when the with statement exits:</p>
@@ -6230,7 +6230,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.inserting_before">
-<span class="sig-name descname"><span class="pre">inserting_before</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.inserting_before" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">inserting_before</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.inserting_before" title="Permalink to this definition">#</a></dt>
 <dd><dl>
 <dt>Set the point at which create_node and companion methods will insert into the graph.</dt><dd><p>When used within a ‘with’ statement, this will temporary set the insert point and
 then restore it when the with statement exits:</p>
@@ -6263,7 +6263,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.lint">
-<span class="sig-name descname"><span class="pre">lint</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.lint" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">lint</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.lint" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs various checks on this Graph to make sure it is well-formed. In
 particular:
 - Checks Nodes have correct ownership (owned by this graph)
@@ -6278,7 +6278,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.node_copy">
-<span class="sig-name descname"><span class="pre">node_copy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg_transform=&lt;function</span> <span class="pre">Graph.&lt;lambda&gt;&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.node_copy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">node_copy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg_transform=&lt;function</span> <span class="pre">Graph.&lt;lambda&gt;&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.node_copy" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy a node from one graph into another. <code class="docutils literal notranslate"><span class="pre">arg_transform</span></code> needs to transform arguments from
 the graph of node to the graph of self. Example:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># Copying all the nodes in `g` into `new_graph`</span>
@@ -6326,7 +6326,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.on_generate_code">
-<span class="sig-name descname"><span class="pre">on_generate_code</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">make_transformer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1944"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.on_generate_code" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">on_generate_code</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">make_transformer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1944"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.on_generate_code" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a transformer function when python code is generated</p>
 <blockquote>
 <div><dl>
@@ -6401,7 +6401,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.output">
-<span class="sig-name descname"><span class="pre">output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">result</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.output" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">result</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.output" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert an <code class="docutils literal notranslate"><span class="pre">output</span></code> <code class="docutils literal notranslate"><span class="pre">Node</span></code> into the <code class="docutils literal notranslate"><span class="pre">Graph</span></code>. An <code class="docutils literal notranslate"><span class="pre">output</span></code> node represents
 a <code class="docutils literal notranslate"><span class="pre">return</span></code> statement in Python code. <code class="docutils literal notranslate"><span class="pre">result</span></code> is the value that should
 be returned.</p>
@@ -6427,7 +6427,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.output_node">
-<span class="sig-name descname"><span class="pre">output_node</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1090"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.output_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">output_node</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1090"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.output_node" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This API is experimental and is <em>NOT</em> backward-compatible.</p>
@@ -6441,7 +6441,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.placeholder">
-<span class="sig-name descname"><span class="pre">placeholder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.placeholder" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">placeholder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.placeholder" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert a <code class="docutils literal notranslate"><span class="pre">placeholder</span></code> node into the Graph. A <code class="docutils literal notranslate"><span class="pre">placeholder</span></code> represents
 a function input.</p>
 <dl class="field-list simple">
@@ -6476,7 +6476,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.print_tabular">
-<span class="sig-name descname"><span class="pre">print_tabular</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.print_tabular" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">print_tabular</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.print_tabular" title="Permalink to this definition">#</a></dt>
 <dd><p>Prints the intermediate representation of the graph in tabular
 format. Note that this API requires the <code class="docutils literal notranslate"><span class="pre">tabulate</span></code> module to be
 installed.</p>
@@ -6488,7 +6488,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.process_inputs">
-<span class="sig-name descname"><span class="pre">process_inputs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1235"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.process_inputs" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">process_inputs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1235"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.process_inputs" title="Permalink to this definition">#</a></dt>
 <dd><p>Processes args so that they can be passed to the FX graph.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -6498,7 +6498,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.process_outputs">
-<span class="sig-name descname"><span class="pre">process_outputs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.process_outputs" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">process_outputs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.process_outputs" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This API is experimental and is <em>NOT</em> backward-compatible.</p>
@@ -6507,7 +6507,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.python_code">
-<span class="sig-name descname"><span class="pre">python_code</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root_module</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">colored</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expanded_def</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1635"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.python_code" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">python_code</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root_module</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">colored</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expanded_def</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1635"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.python_code" title="Permalink to this definition">#</a></dt>
 <dd><p>Turn this <code class="docutils literal notranslate"><span class="pre">Graph</span></code> into valid Python code.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -6530,7 +6530,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Graph.set_codegen">
-<span class="sig-name descname"><span class="pre">set_codegen</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">codegen</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/graph.py#L1940"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.set_codegen" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_codegen</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">codegen</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/graph.py#L1940"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Graph.set_codegen" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This API is experimental and is <em>NOT</em> backward-compatible.</p>
@@ -6543,7 +6543,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.Node">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L209"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L209"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">Node</span></code> is the data structure that represents individual operations within
 a <code class="docutils literal notranslate"><span class="pre">Graph</span></code>. For the most part, Nodes represent callsites to various entities,
 such as operators, methods, and Modules (some exceptions include nodes that
@@ -6591,7 +6591,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.append">
-<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L423"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.append" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L423"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.append" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert <code class="docutils literal notranslate"><span class="pre">x</span></code> after this node in the list of nodes in the graph.
 Equivalent to <code class="docutils literal notranslate"><span class="pre">self.next.prepend(x)</span></code></p>
 <dl class="field-list simple">
@@ -6617,7 +6617,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.format_node">
-<span class="sig-name descname"><span class="pre">format_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholder_names</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maybe_return_typename</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_tensor_metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L600"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.format_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">format_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholder_names</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maybe_return_typename</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_tensor_metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L600"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.format_node" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a descriptive string representation of <code class="docutils literal notranslate"><span class="pre">self</span></code>.</p>
 <p>This method can be used with no arguments as a debugging
 utility.</p>
@@ -6661,7 +6661,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.insert_arg">
-<span class="sig-name descname"><span class="pre">insert_arg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L513"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.insert_arg" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">insert_arg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L513"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.insert_arg" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert an positional argument to the argument list with given index.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -6679,7 +6679,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.is_impure">
-<span class="sig-name descname"><span class="pre">is_impure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">impure_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L753"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.is_impure" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_impure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">impure_random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L753"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.is_impure" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether this op is impure, i.e. if its op is a placeholder or
 output, or if a call_function or call_module which is impure.</p>
 <dl class="field-list simple">
@@ -6722,7 +6722,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.normalized_arguments">
-<span class="sig-name descname"><span class="pre">normalized_arguments</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg_types</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwarg_types</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalize_to_only_use_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L818"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.normalized_arguments" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">normalized_arguments</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg_types</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwarg_types</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalize_to_only_use_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L818"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.normalized_arguments" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns normalized arguments to Python targets. This means that
 <cite>args/kwargs</cite> will be matched up to the module/functional’s
 signature and return exclusively kwargs in positional order
@@ -6755,7 +6755,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.prepend">
-<span class="sig-name descname"><span class="pre">prepend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.prepend" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prepend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.prepend" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert x before this node in the list of nodes in the graph. Example:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">Before</span><span class="p">:</span> <span class="n">p</span> <span class="o">-&gt;</span> <span class="bp">self</span>
         <span class="n">bx</span> <span class="o">-&gt;</span> <span class="n">x</span> <span class="o">-&gt;</span> <span class="n">ax</span>
@@ -6787,7 +6787,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.replace_all_uses_with">
-<span class="sig-name descname"><span class="pre">replace_all_uses_with</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">replace_with</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delete_user_cb=&lt;function</span> <span class="pre">Node.&lt;lambda&gt;&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">propagate_meta=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L694"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.replace_all_uses_with" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">replace_all_uses_with</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">replace_with</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delete_user_cb=&lt;function</span> <span class="pre">Node.&lt;lambda&gt;&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">propagate_meta=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L694"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.replace_all_uses_with" title="Permalink to this definition">#</a></dt>
 <dd><p>Replace all uses of <code class="docutils literal notranslate"><span class="pre">self</span></code> in the Graph with the Node <code class="docutils literal notranslate"><span class="pre">replace_with</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -6816,7 +6816,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.replace_input_with">
-<span class="sig-name descname"><span class="pre">replace_input_with</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">old_input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L870"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.replace_input_with" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">replace_input_with</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">old_input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L870"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.replace_input_with" title="Permalink to this definition">#</a></dt>
 <dd><p>Loop through input nodes of <code class="docutils literal notranslate"><span class="pre">self</span></code>, and replace all instances of
 <code class="docutils literal notranslate"><span class="pre">old_input</span></code> with <code class="docutils literal notranslate"><span class="pre">new_input</span></code>.</p>
 <dl class="field-list simple">
@@ -6847,7 +6847,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.update_arg">
-<span class="sig-name descname"><span class="pre">update_arg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.update_arg" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">update_arg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">idx</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.update_arg" title="Permalink to this definition">#</a></dt>
 <dd><p>Update an existing positional argument to contain the new value
 <code class="docutils literal notranslate"><span class="pre">arg</span></code>. After calling, <code class="docutils literal notranslate"><span class="pre">self.args[idx]</span> <span class="pre">==</span> <span class="pre">arg</span></code>.</p>
 <dl class="field-list simple">
@@ -6866,7 +6866,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Node.update_kwarg">
-<span class="sig-name descname"><span class="pre">update_kwarg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/node.py#L539"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.update_kwarg" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">update_kwarg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">arg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/node.py#L539"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Node.update_kwarg" title="Permalink to this definition">#</a></dt>
 <dd><p>Update an existing keyword argument to contain the new value
 <code class="docutils literal notranslate"><span class="pre">arg</span></code>. After calling, <code class="docutils literal notranslate"><span class="pre">self.kwargs[key]</span> <span class="pre">==</span> <span class="pre">arg</span></code>.</p>
 <dl class="field-list simple">
@@ -6887,7 +6887,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.Tracer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Tracer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">autowrap_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(math,)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autowrap_functions</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L256"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Tracer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">autowrap_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(math,)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autowrap_functions</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L256"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer" title="Permalink to this definition">#</a></dt>
 <dd><blockquote>
 <div><p><code class="docutils literal notranslate"><span class="pre">Tracer</span></code> is the class that implements the symbolic tracing functionality
 of <code class="docutils literal notranslate"><span class="pre">torch.fx.symbolic_trace</span></code>. A call to <code class="docutils literal notranslate"><span class="pre">symbolic_trace(m)</span></code> is equivalent
@@ -6904,7 +6904,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.call_module">
-<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forward</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L511"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.call_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forward</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L511"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.call_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Method that specifies the behavior of this <code class="docutils literal notranslate"><span class="pre">Tracer</span></code> when it encounters
 a call to an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> instance.</p>
 <p>By default, the behavior is to check if the called module is a leaf module
@@ -6940,7 +6940,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.create_arg">
-<span class="sig-name descname"><span class="pre">create_arg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L366"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.create_arg" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_arg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L366"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.create_arg" title="Permalink to this definition">#</a></dt>
 <dd><p>A method to specify the behavior of tracing when preparing values to
 be used as arguments to nodes in the <code class="docutils literal notranslate"><span class="pre">Graph</span></code>.</p>
 <p>By default, the behavior includes:</p>
@@ -6978,7 +6978,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.create_args_for_root">
-<span class="sig-name descname"><span class="pre">create_args_for_root</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concrete_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L634"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.create_args_for_root" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_args_for_root</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concrete_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L634"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.create_args_for_root" title="Permalink to this definition">#</a></dt>
 <dd><p>Create <code class="docutils literal notranslate"><span class="pre">placeholder</span></code> nodes corresponding to the signature of the <code class="docutils literal notranslate"><span class="pre">root</span></code>
 Module. This method introspects root’s signature and emits those
 nodes accordingly, also supporting <code class="docutils literal notranslate"><span class="pre">*args</span></code> and <code class="docutils literal notranslate"><span class="pre">**kwargs</span></code>.</p>
@@ -6990,7 +6990,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.create_node">
-<span class="sig-name descname"><span class="pre">create_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kind</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/proxy.py#L152"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.create_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kind</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/proxy.py#L152"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.create_node" title="Permalink to this definition">#</a></dt>
 <dd><p>Inserts a graph node given target, args, kwargs, and name.</p>
 <p>This method can be overridden to do extra checking, validation, or
 modification of values used in node creation. For example, one might
@@ -7008,7 +7008,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.create_proxy">
-<span class="sig-name descname"><span class="pre">create_proxy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kind</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proxy_factory_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/proxy.py#L263"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.create_proxy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_proxy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kind</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">type_expr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proxy_factory_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/proxy.py#L263"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.create_proxy" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a Node from the given arguments, then return the Node
 wrapped in a Proxy object.</p>
 <p>If kind = ‘placeholder’, then we’re creating a Node that
@@ -7025,7 +7025,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.get_fresh_qualname">
-<span class="sig-name descname"><span class="pre">get_fresh_qualname</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.get_fresh_qualname" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_fresh_qualname</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.get_fresh_qualname" title="Permalink to this definition">#</a></dt>
 <dd><p>Gets a fresh name for a prefix and returns it. This function ensures
 that it will not clash with an existing attribute on the graph.</p>
 <div class="admonition note">
@@ -7041,7 +7041,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.getattr">
-<span class="sig-name descname"><span class="pre">getattr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attr_val</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameter_proxy_cache</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.getattr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">getattr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attr_val</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameter_proxy_cache</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.getattr" title="Permalink to this definition">#</a></dt>
 <dd><p>Method that specifies the behavior of this <code class="docutils literal notranslate"><span class="pre">Tracer</span></code> when we call getattr
 on a call to an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> instance.</p>
 <p>By default, the behavior is to return a proxy value for the attribute. It
@@ -7069,7 +7069,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.is_leaf_module">
-<span class="sig-name descname"><span class="pre">is_leaf_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_qualified_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L459"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.is_leaf_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_leaf_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_qualified_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L459"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.is_leaf_module" title="Permalink to this definition">#</a></dt>
 <dd><p>A method to specify whether a given <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> is a “leaf” module.</p>
 <p>Leaf modules are the atomic units that appear in
 the IR, referenced by <code class="docutils literal notranslate"><span class="pre">call_module</span></code> calls. By default,
@@ -7099,7 +7099,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.iter">
-<span class="sig-name descname"><span class="pre">iter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/proxy.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.iter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">iter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/proxy.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.iter" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Called when a proxy object is being iterated over, such as</dt><dd><p>when used in control flow.  Normally we don’t know what to do because
 we don’t know the value of the proxy, but a custom tracer can attach more
@@ -7119,7 +7119,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.keys">
-<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/proxy.py#L434"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.keys" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/proxy.py#L434"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.keys" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Called when a proxy object is has the keys() method called.</dt><dd><p>This is what happens when ** is called on a proxy. This should return an
 iterator it ** is suppose to work in your custom tracer.</p>
@@ -7138,7 +7138,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.path_of_module">
-<span class="sig-name descname"><span class="pre">path_of_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L484"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.path_of_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">path_of_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L484"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.path_of_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Helper method to find the qualified name of <code class="docutils literal notranslate"><span class="pre">mod</span></code> in the Module hierarchy
 of <code class="docutils literal notranslate"><span class="pre">root</span></code>. For example, if <code class="docutils literal notranslate"><span class="pre">root</span></code> has a submodule named <code class="docutils literal notranslate"><span class="pre">foo</span></code>, which has
 a submodule named <code class="docutils literal notranslate"><span class="pre">bar</span></code>, passing <code class="docutils literal notranslate"><span class="pre">bar</span></code> into this function will return
@@ -7159,7 +7159,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.proxy">
-<span class="sig-name descname"><span class="pre">proxy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/proxy.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.proxy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">proxy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/proxy.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.proxy" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition note">
 <p class="admonition-title">Note</p>
 <p>Backwards-compatibility for this API is guaranteed.</p>
@@ -7173,7 +7173,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.to_bool">
-<span class="sig-name descname"><span class="pre">to_bool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/proxy.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.to_bool" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_bool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/proxy.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.to_bool" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Called when a proxy object is being converted to a boolean, such as</dt><dd><p>when used in control flow.  Normally we don’t know what to do because
 we don’t know the value of the proxy, but a custom tracer can attach more
@@ -7193,7 +7193,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Tracer.trace">
-<span class="sig-name descname"><span class="pre">trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concrete_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/_symbolic_trace.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.trace" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">concrete_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/_symbolic_trace.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Tracer.trace" title="Permalink to this definition">#</a></dt>
 <dd><p>Trace <code class="docutils literal notranslate"><span class="pre">root</span></code> and return the corresponding FX <code class="docutils literal notranslate"><span class="pre">Graph</span></code> representation. <code class="docutils literal notranslate"><span class="pre">root</span></code>
 can either be an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> instance or a Python callable.</p>
 <p>Note that after this call, <code class="docutils literal notranslate"><span class="pre">self.root</span></code> may be different from the <code class="docutils literal notranslate"><span class="pre">root</span></code> passed
@@ -7228,7 +7228,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.Proxy">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Proxy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/proxy.py#L464"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Proxy" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Proxy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/proxy.py#L464"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Proxy" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">Proxy</span></code> objects are <code class="docutils literal notranslate"><span class="pre">Node</span></code> wrappers that flow through the
 program during symbolic tracing and record all the operations
 (<code class="docutils literal notranslate"><span class="pre">torch</span></code> function calls, method calls, operators) that they touch
@@ -7261,7 +7261,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.Interpreter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Interpreter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">garbage_collect_values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Interpreter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">garbage_collect_values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter" title="Permalink to this definition">#</a></dt>
 <dd><p>An Interpreter executes an FX graph Node-by-Node. This pattern
 can be useful for many things, including writing code
 transformations as well as analysis passes.</p>
@@ -7327,7 +7327,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.boxed_run">
-<span class="sig-name descname"><span class="pre">boxed_run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args_list</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.boxed_run" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">boxed_run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args_list</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.boxed_run" title="Permalink to this definition">#</a></dt>
 <dd><p>Run <cite>module</cite> via interpretation and return the result.  This uses the “boxed”
 calling convention, where you pass a list of arguments, which will be cleared
 by the interpreter.  This ensures that input tensors are promptly deallocated.</p>
@@ -7339,7 +7339,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.call_function">
-<span class="sig-name descname"><span class="pre">call_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.call_function" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.call_function" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">call_function</span></code> node and return the result.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -7367,7 +7367,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.call_method">
-<span class="sig-name descname"><span class="pre">call_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.call_method" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.call_method" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">call_method</span></code> node and return the result.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -7395,7 +7395,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.call_module">
-<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.call_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.call_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">call_module</span></code> node and return the result.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -7423,7 +7423,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.fetch_args_kwargs_from_env">
-<span class="sig-name descname"><span class="pre">fetch_args_kwargs_from_env</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.fetch_args_kwargs_from_env" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fetch_args_kwargs_from_env</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.fetch_args_kwargs_from_env" title="Permalink to this definition">#</a></dt>
 <dd><p>Fetch the concrete values of <code class="docutils literal notranslate"><span class="pre">args</span></code> and <code class="docutils literal notranslate"><span class="pre">kwargs</span></code> of node <code class="docutils literal notranslate"><span class="pre">n</span></code>
 from the current execution environment.</p>
 <dl class="field-list simple">
@@ -7445,7 +7445,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.fetch_attr">
-<span class="sig-name descname"><span class="pre">fetch_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.fetch_attr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fetch_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.fetch_attr" title="Permalink to this definition">#</a></dt>
 <dd><p>Fetch an attribute from the <code class="docutils literal notranslate"><span class="pre">Module</span></code> hierarchy of <code class="docutils literal notranslate"><span class="pre">self.module</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -7466,7 +7466,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.get_attr">
-<span class="sig-name descname"><span class="pre">get_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.get_attr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.get_attr" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">get_attr</span></code> node. Will retrieve an attribute
 value from the <code class="docutils literal notranslate"><span class="pre">Module</span></code> hierarchy of <code class="docutils literal notranslate"><span class="pre">self.module</span></code>.</p>
 <dl class="field-list simple">
@@ -7494,7 +7494,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.map_nodes_to_values">
-<span class="sig-name descname"><span class="pre">map_nodes_to_values</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L447"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.map_nodes_to_values" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">map_nodes_to_values</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L447"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.map_nodes_to_values" title="Permalink to this definition">#</a></dt>
 <dd><p>Recursively descend through <code class="docutils literal notranslate"><span class="pre">args</span></code> and look up the concrete value
 for each <code class="docutils literal notranslate"><span class="pre">Node</span></code> in the current execution environment.</p>
 <dl class="field-list simple">
@@ -7516,7 +7516,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.output">
-<span class="sig-name descname"><span class="pre">output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L387"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.output" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L387"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.output" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute an <code class="docutils literal notranslate"><span class="pre">output</span></code> node. This really just retrieves
 the value referenced by the <code class="docutils literal notranslate"><span class="pre">output</span></code> node and returns it.</p>
 <dl class="field-list simple">
@@ -7544,7 +7544,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.placeholder">
-<span class="sig-name descname"><span class="pre">placeholder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.placeholder" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">placeholder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.placeholder" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">placeholder</span></code> node. Note that this is stateful:
 <code class="docutils literal notranslate"><span class="pre">Interpreter</span></code> maintains an internal iterator over
 arguments passed to <code class="docutils literal notranslate"><span class="pre">run</span></code> and this method returns
@@ -7574,7 +7574,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.run">
-<span class="sig-name descname"><span class="pre">run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">initial_env</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_io_processing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.run" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">initial_env</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_io_processing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.run" title="Permalink to this definition">#</a></dt>
 <dd><p>Run <cite>module</cite> via interpretation and return the result.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -7603,7 +7603,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Interpreter.run_node">
-<span class="sig-name descname"><span class="pre">run_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.run_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">run_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Interpreter.run_node" title="Permalink to this definition">#</a></dt>
 <dd><p>Run a specific node <code class="docutils literal notranslate"><span class="pre">n</span></code> and return the result.
 Calls into placeholder, get_attr, call_function,
 call_method, call_module, or output depending
@@ -7629,7 +7629,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.Transformer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Transformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">Transformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">Transformer</span></code> is a special type of interpreter that produces a
 new <code class="docutils literal notranslate"><span class="pre">Module</span></code>. It exposes a <code class="docutils literal notranslate"><span class="pre">transform()</span></code> method that returns
 the transformed <code class="docutils literal notranslate"><span class="pre">Module</span></code>. <code class="docutils literal notranslate"><span class="pre">Transformer</span></code> does not require
@@ -7684,7 +7684,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Transformer.call_function">
-<span class="sig-name descname"><span class="pre">call_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L590"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.call_function" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L590"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.call_function" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition note">
 <p class="admonition-title">Note</p>
 <p>Backwards-compatibility for this API is guaranteed.</p>
@@ -7698,7 +7698,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Transformer.call_module">
-<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L581"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.call_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L581"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.call_module" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition note">
 <p class="admonition-title">Note</p>
 <p>Backwards-compatibility for this API is guaranteed.</p>
@@ -7712,7 +7712,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Transformer.get_attr">
-<span class="sig-name descname"><span class="pre">get_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L562"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.get_attr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L562"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.get_attr" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">get_attr</span></code> node. In <code class="docutils literal notranslate"><span class="pre">Transformer</span></code>, this is
 overridden to insert a new <code class="docutils literal notranslate"><span class="pre">get_attr</span></code> node into the output
 graph.</p>
@@ -7738,7 +7738,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Transformer.placeholder">
-<span class="sig-name descname"><span class="pre">placeholder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.placeholder" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">placeholder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.placeholder" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">placeholder</span></code> node. In <code class="docutils literal notranslate"><span class="pre">Transformer</span></code>, this is
 overridden to insert a new <code class="docutils literal notranslate"><span class="pre">placeholder</span></code> into the output
 graph.</p>
@@ -7764,7 +7764,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.Transformer.transform">
-<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.transform" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">transform</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.Transformer.transform" title="Permalink to this definition">#</a></dt>
 <dd><p>Transform <code class="docutils literal notranslate"><span class="pre">self.module</span></code> and return the transformed
 <code class="docutils literal notranslate"><span class="pre">GraphModule</span></code>.</p>
 <div class="admonition note">
@@ -7782,7 +7782,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.replace_pattern">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">replace_pattern</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">gm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pattern</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">replacement</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/subgraph_rewriter.py#L94"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.replace_pattern" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.</span></span><span class="sig-name descname"><span class="pre">replace_pattern</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">gm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pattern</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">replacement</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/subgraph_rewriter.py#L94"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.replace_pattern" title="Permalink to this definition">#</a></dt>
 <dd><p>Matches all possible non-overlapping sets of operators and their
 data dependencies (<code class="docutils literal notranslate"><span class="pre">pattern</span></code>) in the Graph of a GraphModule
 (<code class="docutils literal notranslate"><span class="pre">gm</span></code>), then replaces each of these matched subgraphs with another
diff --git a/2.9/generated/torch.Tensor.backward.html b/2.9/generated/torch.Tensor.backward.html
index 79914b67c08..acca3c7c159 100644
--- a/2.9/generated/torch.Tensor.backward.html
+++ b/2.9/generated/torch.Tensor.backward.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.backward<a class="headerlink" href="#torch-tensor-backward" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.backward">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">gradient</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">gradient</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the gradient of current tensor wrt graph leaves.</p>
 <p>The graph is differentiated using the chain rule. If the tensor is
 non-scalar (i.e. its data has more than one element) and requires
diff --git a/2.9/generated/torch.Tensor.dim_order.html b/2.9/generated/torch.Tensor.dim_order.html
index 9baa48b47e0..57b4b0553dc 100644
--- a/2.9/generated/torch.Tensor.dim_order.html
+++ b/2.9/generated/torch.Tensor.dim_order.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.dim_order<a class="headerlink" href="#torch-tensor-dim-order" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.dim_order">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">dim_order</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ambiguity_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1490"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.dim_order" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">dim_order</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ambiguity_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1490"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.dim_order" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the uniquely determined tuple of int describing the dim order or
 physical layout of <code class="xref py py-attr docutils literal notranslate"><span class="pre">self</span></code>.</p>
 <p>The dim order represents how dimensions are laid out in memory of dense tensors,
diff --git a/2.9/generated/torch.Tensor.is_shared.html b/2.9/generated/torch.Tensor.is_shared.html
index 3bb21ed9cad..daa64fd8727 100644
--- a/2.9/generated/torch.Tensor.is_shared.html
+++ b/2.9/generated/torch.Tensor.is_shared.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.is_shared<a class="headerlink" href="#torch-tensor-is-shared" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.is_shared">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">is_shared</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L798"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.is_shared" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">is_shared</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L798"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.is_shared" title="Permalink to this definition">#</a></dt>
 <dd><p>Checks if tensor is in shared memory.</p>
 <p>This is always <code class="docutils literal notranslate"><span class="pre">True</span></code> for CUDA tensors.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.Tensor.istft.html b/2.9/generated/torch.Tensor.istft.html
index 5edef549278..c9d8b99eb34 100644
--- a/2.9/generated/torch.Tensor.istft.html
+++ b/2.9/generated/torch.Tensor.istft.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.istft<a class="headerlink" href="#torch-tensor-istft" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.istft">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">istft</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_fft</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">win_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onesided</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L958"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.istft" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">istft</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_fft</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">win_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onesided</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L958"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.istft" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.istft.html#torch.istft" title="torch.istft"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.istft()</span></code></a></p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.Tensor.lu.html b/2.9/generated/torch.Tensor.lu.html
index c77df769349..4fd224c3aad 100644
--- a/2.9/generated/torch.Tensor.lu.html
+++ b/2.9/generated/torch.Tensor.lu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.lu<a class="headerlink" href="#torch-tensor-lu" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.lu">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">lu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pivot</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">get_infos</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L893"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.lu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">lu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pivot</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">get_infos</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L893"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.lu" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.lu.html#torch.lu" title="torch.lu"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.lu()</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.Tensor.module_load.html b/2.9/generated/torch.Tensor.module_load.html
index f9aaff1d0ce..ae7bf3dcc3d 100644
--- a/2.9/generated/torch.Tensor.module_load.html
+++ b/2.9/generated/torch.Tensor.module_load.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.module_load<a class="headerlink" href="#torch-tensor-module-load" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.module_load">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">module_load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">other</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assign</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L820"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.module_load" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">module_load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">other</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assign</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L820"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.module_load" title="Permalink to this definition">#</a></dt>
 <dd><p>Defines how to transform <code class="docutils literal notranslate"><span class="pre">other</span></code> when loading it into <code class="docutils literal notranslate"><span class="pre">self</span></code> in <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module.load_state_dict" title="torch.nn.Module.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a>.</p>
 <p>Used when <a class="reference internal" href="../future_mod.html#torch.__future__.get_swap_module_params_on_conversion" title="torch.__future__.get_swap_module_params_on_conversion"><code class="xref py py-func docutils literal notranslate"><span class="pre">get_swap_module_params_on_conversion()</span></code></a> is <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
 <p>It is expected that <code class="docutils literal notranslate"><span class="pre">self</span></code> is a parameter or buffer in an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> and <code class="docutils literal notranslate"><span class="pre">other</span></code> is the
diff --git a/2.9/generated/torch.Tensor.norm.html b/2.9/generated/torch.Tensor.norm.html
index 690190f3299..f53d5abe1a0 100644
--- a/2.9/generated/torch.Tensor.norm.html
+++ b/2.9/generated/torch.Tensor.norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.norm<a class="headerlink" href="#torch-tensor-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.norm">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fro'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L859"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fro'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L859"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.norm" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.norm.html#torch.norm" title="torch.norm"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.norm()</span></code></a></p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.Tensor.register_hook.html b/2.9/generated/torch.Tensor.register_hook.html
index e5bd14dfbfb..620cfdf7d8c 100644
--- a/2.9/generated/torch.Tensor.register_hook.html
+++ b/2.9/generated/torch.Tensor.register_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.register_hook<a class="headerlink" href="#torch-tensor-register-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.register_hook">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">register_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L629"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.register_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">register_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L629"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.register_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a backward hook.</p>
 <p>The hook will be called every time a gradient with respect to the
 Tensor is computed. The hook should have the following signature:</p>
diff --git a/2.9/generated/torch.Tensor.register_post_accumulate_grad_hook.html b/2.9/generated/torch.Tensor.register_post_accumulate_grad_hook.html
index d7381bad672..b2925b2425a 100644
--- a/2.9/generated/torch.Tensor.register_post_accumulate_grad_hook.html
+++ b/2.9/generated/torch.Tensor.register_post_accumulate_grad_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.register_post_accumulate_grad_hook<a class="headerlink" href="#torch-tensor-register-post-accumulate-grad-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.register_post_accumulate_grad_hook">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">register_post_accumulate_grad_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L679"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.register_post_accumulate_grad_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">register_post_accumulate_grad_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L679"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.register_post_accumulate_grad_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a backward hook that runs after grad accumulation.</p>
 <p>The hook will be called after all gradients for a tensor have been accumulated,
 meaning that the .grad field has been updated on that tensor. The post
diff --git a/2.9/generated/torch.Tensor.share_memory_.html b/2.9/generated/torch.Tensor.share_memory_.html
index 35ba80985f7..aa1d2fc7185 100644
--- a/2.9/generated/torch.Tensor.share_memory_.html
+++ b/2.9/generated/torch.Tensor.share_memory_.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.share_memory_<a class="headerlink" href="#torch-tensor-share-memory" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.share_memory_">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">share_memory_</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.share_memory_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">share_memory_</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.share_memory_" title="Permalink to this definition">#</a></dt>
 <dd><p>Moves the underlying storage to shared memory.</p>
 <p>This is a no-op if the underlying storage is already in shared memory
 and for CUDA tensors. Tensors in shared memory cannot be resized.</p>
diff --git a/2.9/generated/torch.Tensor.split.html b/2.9/generated/torch.Tensor.split.html
index f0b0fe7233d..68afa48c6f3 100644
--- a/2.9/generated/torch.Tensor.split.html
+++ b/2.9/generated/torch.Tensor.split.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.split<a class="headerlink" href="#torch-tensor-split" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.split">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">split_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1015"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.split" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">split_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1015"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.split" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.split.html#torch.split" title="torch.split"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.split()</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.Tensor.stft.html b/2.9/generated/torch.Tensor.stft.html
index 3f7c68d11c6..762f8f69cc7 100644
--- a/2.9/generated/torch.Tensor.stft.html
+++ b/2.9/generated/torch.Tensor.stft.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.stft<a class="headerlink" href="#torch-tensor-stft" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.stft">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">stft</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_fft</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">win_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reflect'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onesided</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_to_window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L909"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.stft" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">stft</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_fft</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">win_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reflect'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onesided</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_to_window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L909"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.stft" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.stft.html#torch.stft" title="torch.stft"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.stft()</span></code></a></p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.Tensor.storage.html b/2.9/generated/torch.Tensor.storage.html
index 3e4c3ed7b19..740d2030d42 100644
--- a/2.9/generated/torch.Tensor.storage.html
+++ b/2.9/generated/torch.Tensor.storage.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.storage<a class="headerlink" href="#torch-tensor-storage" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.storage">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">storage</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../storage.html#torch.TypedStorage" title="torch.TypedStorage"><span class="pre">torch.TypedStorage</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.storage" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">storage</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../storage.html#torch.TypedStorage" title="torch.TypedStorage"><span class="pre">torch.TypedStorage</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.storage" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the underlying <a class="reference internal" href="../storage.html#torch.TypedStorage" title="torch.TypedStorage"><code class="xref py py-class docutils literal notranslate"><span class="pre">TypedStorage</span></code></a>.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.Tensor.storage_type.html b/2.9/generated/torch.Tensor.storage_type.html
index 92c7cfccac8..1cc2f04e793 100644
--- a/2.9/generated/torch.Tensor.storage_type.html
+++ b/2.9/generated/torch.Tensor.storage_type.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.storage_type<a class="headerlink" href="#torch-tensor-storage-type" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.storage_type">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">storage_type</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/functions.html#type" title="(in Python v3.14)"><span class="pre">type</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1296"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.storage_type" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">storage_type</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/functions.html#type" title="(in Python v3.14)"><span class="pre">type</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1296"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.storage_type" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the type of the underlying storage.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.Tensor.to_sparse_coo.html b/2.9/generated/torch.Tensor.to_sparse_coo.html
index 971aef0fedb..7f147e637f8 100644
--- a/2.9/generated/torch.Tensor.to_sparse_coo.html
+++ b/2.9/generated/torch.Tensor.to_sparse_coo.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.to_sparse_coo<a class="headerlink" href="#torch-tensor-to-sparse-coo" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.to_sparse_coo">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">to_sparse_coo</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1477"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.to_sparse_coo" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">to_sparse_coo</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1477"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.to_sparse_coo" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert a tensor to <a class="reference internal" href="../sparse.html#sparse-coo-docs"><span class="std std-ref">coordinate format</span></a>.</p>
 <p>Examples:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">dense</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="mi">5</span><span class="p">,</span> <span class="mi">5</span><span class="p">)</span>
diff --git a/2.9/generated/torch.Tensor.unflatten.html b/2.9/generated/torch.Tensor.unflatten.html
index cb1c76beba1..a9fe2dbc1ac 100644
--- a/2.9/generated/torch.Tensor.unflatten.html
+++ b/2.9/generated/torch.Tensor.unflatten.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.unflatten<a class="headerlink" href="#torch-tensor-unflatten" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.unflatten">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">unflatten</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sizes</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1398"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.unflatten" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">unflatten</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sizes</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1398"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.unflatten" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.unflatten.html#torch.unflatten" title="torch.unflatten"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.unflatten()</span></code></a>.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.Tensor.unique.html b/2.9/generated/torch.Tensor.unique.html
index d57534608e8..8274c2e286b 100644
--- a/2.9/generated/torch.Tensor.unique.html
+++ b/2.9/generated/torch.Tensor.unique.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.unique<a class="headerlink" href="#torch-tensor-unique" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.unique">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">unique</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_inverse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_counts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1032"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.unique" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">unique</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_inverse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_counts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1032"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.unique" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the unique elements of the input tensor.</p>
 <p>See <a class="reference internal" href="torch.unique.html#torch.unique" title="torch.unique"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.unique()</span></code></a></p>
 </dd></dl>
diff --git a/2.9/generated/torch.Tensor.unique_consecutive.html b/2.9/generated/torch.Tensor.unique_consecutive.html
index 75c4722f5e2..d964778f5fb 100644
--- a/2.9/generated/torch.Tensor.unique_consecutive.html
+++ b/2.9/generated/torch.Tensor.unique_consecutive.html
@@ -4404,7 +4404,7 @@
 <h1>torch.Tensor.unique_consecutive<a class="headerlink" href="#torch-tensor-unique-consecutive" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.unique_consecutive">
-<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">unique_consecutive</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">return_inverse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_counts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1055"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.unique_consecutive" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Tensor.</span></span><span class="sig-name descname"><span class="pre">unique_consecutive</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">return_inverse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_counts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1055"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.unique_consecutive" title="Permalink to this definition">#</a></dt>
 <dd><p>Eliminates all but the first element from every consecutive group of equivalent elements.</p>
 <p>See <a class="reference internal" href="torch.unique_consecutive.html#torch.unique_consecutive" title="torch.unique_consecutive"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.unique_consecutive()</span></code></a></p>
 </dd></dl>
diff --git a/2.9/generated/torch._assert.html b/2.9/generated/torch._assert.html
index 5bcf39a27f4..ade0bb50f3f 100644
--- a/2.9/generated/torch._assert.html
+++ b/2.9/generated/torch._assert.html
@@ -4404,7 +4404,7 @@
 <h1>torch._assert<a class="headerlink" href="#torch-assert" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._assert">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">_assert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">condition</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">message</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L2177"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._assert" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">_assert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">condition</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">message</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L2177"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._assert" title="Permalink to this definition">#</a></dt>
 <dd><p>A wrapper around Python’s assert which is symbolically traceable.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch._logging.set_logs.html b/2.9/generated/torch._logging.set_logs.html
index f17dcf9e529..bf60c39cc26 100644
--- a/2.9/generated/torch._logging.set_logs.html
+++ b/2.9/generated/torch._logging.set_logs.html
@@ -4421,7 +4421,7 @@
 <h1>torch._logging.set_logs<a class="headerlink" href="#torch-logging-set-logs" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._logging.set_logs">
-<span class="sig-prename descclassname"><span class="pre">torch._logging.</span></span><span class="sig-name descname"><span class="pre">set_logs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">all</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">aot</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autograd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inductor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">distributed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">c10d</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ddp</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fsdp</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onnx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bytecode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">aot_graphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">aot_joint_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ddp_graphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_code</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_code_verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_breaks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompiles</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompiles_verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trace_source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trace_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trace_bytecode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_code</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_code</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schedule</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">perf_hints</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pre_grad_graphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">post_grad_graphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ir_pre_fusion</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ir_post_fusion</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onnx_diagnostics</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fusion</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">overlap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cudagraphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compiled_autograd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compiled_autograd_verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cudagraph_static_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">benchmarking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autotuning</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_region_expansion</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inductor_metrics</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hierarchical_compile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_logging/_internal.py#L205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._logging.set_logs" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._logging.</span></span><span class="sig-name descname"><span class="pre">set_logs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">all</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">aot</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autograd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inductor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">distributed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">c10d</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ddp</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fsdp</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onnx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bytecode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">aot_graphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">aot_joint_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ddp_graphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_code</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_code_verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_breaks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompiles</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompiles_verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trace_source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trace_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trace_bytecode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_code</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_code</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schedule</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">perf_hints</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pre_grad_graphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">post_grad_graphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ir_pre_fusion</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ir_post_fusion</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onnx_diagnostics</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fusion</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">overlap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cudagraphs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compiled_autograd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compiled_autograd_verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cudagraph_static_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">benchmarking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autotuning</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph_region_expansion</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inductor_metrics</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hierarchical_compile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_logging/_internal.py#L205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._logging.set_logs" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the log level for individual components and toggles individual log
 artifact types.</p>
 <div class="admonition warning">
diff --git a/2.9/generated/torch.accelerator.current_accelerator.html b/2.9/generated/torch.accelerator.current_accelerator.html
index d0f8aeee808..ebe0a802034 100644
--- a/2.9/generated/torch.accelerator.current_accelerator.html
+++ b/2.9/generated/torch.accelerator.current_accelerator.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.current_accelerator<a class="headerlink" href="#torch-accelerator-current-accelerator" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.current_accelerator">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">current_accelerator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">check_available</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L94"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.current_accelerator" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">current_accelerator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">check_available</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L94"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.current_accelerator" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the device of the accelerator available at compilation time.
 If no accelerator were available at compilation time, returns None.
 See <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a> for details.</p>
diff --git a/2.9/generated/torch.accelerator.current_device_idx.html b/2.9/generated/torch.accelerator.current_device_idx.html
index 7f7bc4276ed..23e6470bbc9 100644
--- a/2.9/generated/torch.accelerator.current_device_idx.html
+++ b/2.9/generated/torch.accelerator.current_device_idx.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.current_device_idx<a class="headerlink" href="#torch-accelerator-current-device-idx" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.current_device_idx">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">current_device_idx</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.current_device_idx" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">current_device_idx</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.current_device_idx" title="Permalink to this definition">#</a></dt>
 <dd><p>(Deprecated) Return the index of a currently selected device for the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
diff --git a/2.9/generated/torch.accelerator.current_device_index.html b/2.9/generated/torch.accelerator.current_device_index.html
index 724728e524c..b41694031d1 100644
--- a/2.9/generated/torch.accelerator.current_device_index.html
+++ b/2.9/generated/torch.accelerator.current_device_index.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.current_device_index<a class="headerlink" href="#torch-accelerator-current-device-index" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.current_device_index">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">current_device_index</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.current_device_index" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">current_device_index</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.current_device_index" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the index of a currently selected device for the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
diff --git a/2.9/generated/torch.accelerator.current_stream.html b/2.9/generated/torch.accelerator.current_stream.html
index 36807cc1141..b2615d98a27 100644
--- a/2.9/generated/torch.accelerator.current_stream.html
+++ b/2.9/generated/torch.accelerator.current_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.current_stream<a class="headerlink" href="#torch-accelerator-current-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.current_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.current_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.current_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the currently selected stream for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.accelerator.device_count.html b/2.9/generated/torch.accelerator.device_count.html
index 834da0a4951..abdaa65f36f 100644
--- a/2.9/generated/torch.accelerator.device_count.html
+++ b/2.9/generated/torch.accelerator.device_count.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.device_count<a class="headerlink" href="#torch-accelerator-device-count" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.device_count">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.device_count" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.device_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the number of current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a> available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
diff --git a/2.9/generated/torch.accelerator.device_index.html b/2.9/generated/torch.accelerator.device_index.html
index 30dc54ca639..86e55b1984c 100644
--- a/2.9/generated/torch.accelerator.device_index.html
+++ b/2.9/generated/torch.accelerator.device_index.html
@@ -4404,7 +4404,7 @@
 <h1>device_index<a class="headerlink" href="#device-index" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.accelerator.device_index">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">device_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.device_index" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">device_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.device_index" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager to set the current device index for the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a>.
 Temporarily changes the current device index to the specified value for the duration
 of the context, and automatically restores the previous device index when exiting
diff --git a/2.9/generated/torch.accelerator.is_available.html b/2.9/generated/torch.accelerator.is_available.html
index 048409fc4b9..5bef7a6f54d 100644
--- a/2.9/generated/torch.accelerator.is_available.html
+++ b/2.9/generated/torch.accelerator.is_available.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.is_available<a class="headerlink" href="#torch-accelerator-is-available" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L65"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L65"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if the current accelerator is available at runtime: it was build, all the
 required drivers are available and at least one device is visible.
 See <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a> for details.</p>
diff --git a/2.9/generated/torch.accelerator.memory.empty_cache.html b/2.9/generated/torch.accelerator.memory.empty_cache.html
index dff18c7e07e..22af2c96428 100644
--- a/2.9/generated/torch.accelerator.memory.empty_cache.html
+++ b/2.9/generated/torch.accelerator.memory.empty_cache.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.memory.empty_cache<a class="headerlink" href="#torch-accelerator-memory-empty-cache" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.memory.empty_cache">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/memory.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.empty_cache" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/memory.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.empty_cache" title="Permalink to this definition">#</a></dt>
 <dd><p>Release all unoccupied cached memory currently held by the caching
 allocator so that those can be used in other application.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.accelerator.memory.max_memory_allocated.html b/2.9/generated/torch.accelerator.memory.max_memory_allocated.html
index 5660f944b7a..46b7105c196 100644
--- a/2.9/generated/torch.accelerator.memory.max_memory_allocated.html
+++ b/2.9/generated/torch.accelerator.memory.max_memory_allocated.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.memory.max_memory_allocated<a class="headerlink" href="#torch-accelerator-memory-max-memory-allocated" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.memory.max_memory_allocated">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/memory.py#L123"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.max_memory_allocated" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/memory.py#L123"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.max_memory_allocated" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a> maximum device memory occupied by tensors
 in bytes for a given device index.</p>
 <p>By default, this returns the peak allocated memory since the beginning of
diff --git a/2.9/generated/torch.accelerator.memory.max_memory_reserved.html b/2.9/generated/torch.accelerator.memory.max_memory_reserved.html
index 71f8ad18c7f..2a8e830b27f 100644
--- a/2.9/generated/torch.accelerator.memory.max_memory_reserved.html
+++ b/2.9/generated/torch.accelerator.memory.max_memory_reserved.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.memory.max_memory_reserved<a class="headerlink" href="#torch-accelerator-memory-max-memory-reserved" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.memory.max_memory_reserved">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/memory.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.max_memory_reserved" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/memory.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.max_memory_reserved" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a> maximum device memory managed by the caching allocator
 in bytes for a given device index.</p>
 <p>By default, this returns the peak cached memory since the beginning of this
diff --git a/2.9/generated/torch.accelerator.memory.memory_allocated.html b/2.9/generated/torch.accelerator.memory.memory_allocated.html
index 15f6e9426c6..d2b60ce0bc8 100644
--- a/2.9/generated/torch.accelerator.memory.memory_allocated.html
+++ b/2.9/generated/torch.accelerator.memory.memory_allocated.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.memory.memory_allocated<a class="headerlink" href="#torch-accelerator-memory-memory-allocated" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.memory.memory_allocated">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/memory.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.memory_allocated" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/memory.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.memory_allocated" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a> device memory occupied by tensors
 in bytes for a given device index.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.accelerator.memory.memory_reserved.html b/2.9/generated/torch.accelerator.memory.memory_reserved.html
index 7c968e84c1f..0715c6776a7 100644
--- a/2.9/generated/torch.accelerator.memory.memory_reserved.html
+++ b/2.9/generated/torch.accelerator.memory.memory_reserved.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.memory.memory_reserved<a class="headerlink" href="#torch-accelerator-memory-memory-reserved" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.memory.memory_reserved">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/memory.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.memory_reserved" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/memory.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.memory_reserved" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a> device memory managed by the caching allocator
 in bytes for a given device index.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.accelerator.memory.memory_stats.html b/2.9/generated/torch.accelerator.memory.memory_stats.html
index 58811612dc5..4020b251fb9 100644
--- a/2.9/generated/torch.accelerator.memory.memory_stats.html
+++ b/2.9/generated/torch.accelerator.memory.memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.memory.memory_stats<a class="headerlink" href="#torch-accelerator-memory-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.memory.memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/memory.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/memory.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary of accelerator device memory allocator statistics for a given device index.</p>
 <p>The return value of this function is a dictionary of statistics, each of
 which is a non-negative integer.</p>
diff --git a/2.9/generated/torch.accelerator.memory.reset_accumulated_memory_stats.html b/2.9/generated/torch.accelerator.memory.reset_accumulated_memory_stats.html
index 6f0566a3bf3..2ea6c53b47a 100644
--- a/2.9/generated/torch.accelerator.memory.reset_accumulated_memory_stats.html
+++ b/2.9/generated/torch.accelerator.memory.reset_accumulated_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.memory.reset_accumulated_memory_stats<a class="headerlink" href="#torch-accelerator-memory-reset-accumulated-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.memory.reset_accumulated_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">reset_accumulated_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/memory.py#L170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.reset_accumulated_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">reset_accumulated_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/memory.py#L170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.reset_accumulated_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the “accumulated” (historical) stats tracked by the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a>
 memory allocator for a given device index.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.accelerator.memory.reset_peak_memory_stats.html b/2.9/generated/torch.accelerator.memory.reset_peak_memory_stats.html
index 365d04f1b7e..4cc09e7e231 100644
--- a/2.9/generated/torch.accelerator.memory.reset_peak_memory_stats.html
+++ b/2.9/generated/torch.accelerator.memory.reset_peak_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.memory.reset_peak_memory_stats<a class="headerlink" href="#torch-accelerator-memory-reset-peak-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.memory.reset_peak_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">reset_peak_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/memory.py#L187"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.reset_peak_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.memory.</span></span><span class="sig-name descname"><span class="pre">reset_peak_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/memory.py#L187"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.memory.reset_peak_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the “peak” stats tracked by the current <a class="reference internal" href="../torch.html#accelerators"><span class="std std-ref">accelerator</span></a>
 memory allocator for a given device index.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.accelerator.set_device_idx.html b/2.9/generated/torch.accelerator.set_device_idx.html
index f06bc3ad7a1..4716dcff2d8 100644
--- a/2.9/generated/torch.accelerator.set_device_idx.html
+++ b/2.9/generated/torch.accelerator.set_device_idx.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.set_device_idx<a class="headerlink" href="#torch-accelerator-set-device-idx" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.set_device_idx">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">set_device_idx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.set_device_idx" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">set_device_idx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.set_device_idx" title="Permalink to this definition">#</a></dt>
 <dd><p>(Deprecated) Set the current device index to a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.accelerator.set_device_index.html b/2.9/generated/torch.accelerator.set_device_index.html
index aba5e957fb3..692ba469fbb 100644
--- a/2.9/generated/torch.accelerator.set_device_index.html
+++ b/2.9/generated/torch.accelerator.set_device_index.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.set_device_index<a class="headerlink" href="#torch-accelerator-set-device-index" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.set_device_index">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">set_device_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.set_device_index" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">set_device_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.set_device_index" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the current device index to a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.accelerator.set_stream.html b/2.9/generated/torch.accelerator.set_stream.html
index 7ef0930c336..4f4d61a0b63 100644
--- a/2.9/generated/torch.accelerator.set_stream.html
+++ b/2.9/generated/torch.accelerator.set_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.set_stream<a class="headerlink" href="#torch-accelerator-set-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.set_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">set_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L200"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.set_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">set_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L200"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.set_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the current stream to a given stream.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.accelerator.synchronize.html b/2.9/generated/torch.accelerator.synchronize.html
index 5d8f7bf7428..ad911c76718 100644
--- a/2.9/generated/torch.accelerator.synchronize.html
+++ b/2.9/generated/torch.accelerator.synchronize.html
@@ -4404,7 +4404,7 @@
 <h1>torch.accelerator.synchronize<a class="headerlink" href="#torch-accelerator-synchronize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.accelerator.synchronize">
-<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/accelerator/__init__.py#L211"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.accelerator.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/accelerator/__init__.py#L211"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.accelerator.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait for all kernels in all streams on the given device to complete.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.BNReLU2d.html b/2.9/generated/torch.ao.nn.intrinsic.BNReLU2d.html
index 6cae876b7d8..96a3ebbde85 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.BNReLU2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.BNReLU2d.html
@@ -4415,7 +4415,7 @@
 <h1>BNReLU2d<a class="headerlink" href="#bnrelu2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.BNReLU2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">BNReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L198"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.BNReLU2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">BNReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L198"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.BNReLU2d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the BatchNorm 2d and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.BNReLU3d.html b/2.9/generated/torch.ao.nn.intrinsic.BNReLU3d.html
index 1809adf648c..82258eee810 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.BNReLU3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.BNReLU3d.html
@@ -4415,7 +4415,7 @@
 <h1>BNReLU3d<a class="headerlink" href="#bnrelu3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.BNReLU3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">BNReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.BNReLU3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">BNReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.BNReLU3d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the BatchNorm 3d and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvBn1d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvBn1d.html
index cedb337ea93..8a28db689c7 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvBn1d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvBn1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBn1d<a class="headerlink" href="#convbn1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvBn1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBn1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBn1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBn1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBn1d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv 1d and Batch Norm 1d modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvBn2d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvBn2d.html
index 787035d6934..9d784567485 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvBn2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvBn2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBn2d<a class="headerlink" href="#convbn2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvBn2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBn2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBn2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBn2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBn2d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv 2d and Batch Norm 2d modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvBn3d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvBn3d.html
index 523c90d47d1..cd571ae86c7 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvBn3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvBn3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBn3d<a class="headerlink" href="#convbn3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvBn3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBn3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L166"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBn3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBn3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L166"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBn3d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv 3d and Batch Norm 3d modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU1d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU1d.html
index f09533b2926..5e670897d2d 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU1d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBnReLU1d<a class="headerlink" href="#convbnrelu1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvBnReLU1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L132"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBnReLU1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L132"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBnReLU1d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv 1d, Batch Norm 1d, and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU2d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU2d.html
index 41c1f073c69..97024adb606 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBnReLU2d<a class="headerlink" href="#convbnrelu2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvBnReLU2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBnReLU2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBnReLU2d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv 2d, Batch Norm 2d, and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU3d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU3d.html
index 748896e1cc5..45c5091dde6 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvBnReLU3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBnReLU3d<a class="headerlink" href="#convbnrelu3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvBnReLU3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBnReLU3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvBnReLU3d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv 3d, Batch Norm 3d, and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvReLU1d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvReLU1d.html
index e05ace35843..6c7d57e0bc2 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvReLU1d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvReLU1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvReLU1d<a class="headerlink" href="#convrelu1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvReLU1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvReLU1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvReLU1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvReLU1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvReLU1d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv1d and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvReLU2d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvReLU2d.html
index 9635e174fe7..f489f031a5f 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvReLU2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvReLU2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvReLU2d<a class="headerlink" href="#convrelu2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvReLU2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvReLU2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvReLU2d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv2d and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.ConvReLU3d.html b/2.9/generated/torch.ao.nn.intrinsic.ConvReLU3d.html
index a5cc7764d86..685feee5927 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.ConvReLU3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.ConvReLU3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvReLU3d<a class="headerlink" href="#convrelu3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.ConvReLU3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvReLU3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">ConvReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.ConvReLU3d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Conv3d and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.LinearReLU.html b/2.9/generated/torch.ao.nn.intrinsic.LinearReLU.html
index 52665678fb6..0537240d67e 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.LinearReLU.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.LinearReLU.html
@@ -4415,7 +4415,7 @@
 <h1>LinearReLU<a class="headerlink" href="#linearrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.LinearReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">LinearReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/modules/fused.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.LinearReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.</span></span><span class="sig-name descname"><span class="pre">LinearReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relu</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/modules/fused.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.LinearReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>This is a sequential container which calls the Linear and ReLU modules.
 During quantization this will be replaced with the corresponding fused module.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn1d.html b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn1d.html
index 4c0586614c7..db6c3992b61 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn1d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBn1d<a class="headerlink" href="#convbn1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.ConvBn1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBn1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L442"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBn1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBn1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L442"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBn1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvBn1d module is a module fused from Conv1d and BatchNorm1d,
 attached with FakeQuantize modules for weight,
 used in quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn2d.html b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn2d.html
index 433f063b460..5b877171653 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBn2d<a class="headerlink" href="#convbn2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.ConvBn2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBn2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L642"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBn2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBn2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L642"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBn2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvBn2d module is a module fused from Conv2d and BatchNorm2d,
 attached with FakeQuantize modules for weight,
 used in quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn3d.html b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn3d.html
index 5de32e0a172..d63d577d912 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBn3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBn3d<a class="headerlink" href="#convbn3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.ConvBn3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBn3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L842"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBn3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBn3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L842"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBn3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvBn3d module is a module fused from Conv3d and BatchNorm3d,
 attached with FakeQuantize modules for weight,
 used in quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU1d.html b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU1d.html
index 5367c9745d4..503c02a96b6 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU1d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBnReLU1d<a class="headerlink" href="#convbnrelu1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.ConvBnReLU1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L512"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBnReLU1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L512"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBnReLU1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvBnReLU1d module is a module fused from Conv1d, BatchNorm1d and ReLU,
 attached with FakeQuantize modules for weight,
 used in quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU2d.html b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU2d.html
index bf8fe82dc24..776d1d4ac11 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBnReLU2d<a class="headerlink" href="#convbnrelu2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.ConvBnReLU2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L712"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBnReLU2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L712"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBnReLU2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvBnReLU2d module is a module fused from Conv2d, BatchNorm2d and ReLU,
 attached with FakeQuantize modules for weight,
 used in quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU3d.html b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU3d.html
index 0130d8b6af2..4d5444e6b38 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvBnReLU3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvBnReLU3d<a class="headerlink" href="#convbnrelu3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.ConvBnReLU3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L912"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBnReLU3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvBnReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze_bn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L912"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvBnReLU3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvBnReLU3d module is a module fused from Conv3d, BatchNorm3d and ReLU,
 attached with FakeQuantize modules for weight,
 used in quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvReLU2d.html b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvReLU2d.html
index 8b5acf2781d..409b24e3cca 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvReLU2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvReLU2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvReLU2d<a class="headerlink" href="#convrelu2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.ConvReLU2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L783"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvReLU2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L783"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvReLU2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvReLU2d module is a fused module of Conv2d and ReLU, attached with
 FakeQuantize modules for weight for
 quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvReLU3d.html b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvReLU3d.html
index 769e57b839d..5774e34af44 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.ConvReLU3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.ConvReLU3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvReLU3d<a class="headerlink" href="#convrelu3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.ConvReLU3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L984"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvReLU3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">ConvReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L984"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.ConvReLU3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvReLU3d module is a fused module of Conv3d and ReLU, attached with
 FakeQuantize modules for weight for
 quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.LinearReLU.html b/2.9/generated/torch.ao.nn.intrinsic.qat.LinearReLU.html
index e5555bf51e5..40c465c6125 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.LinearReLU.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.LinearReLU.html
@@ -4415,7 +4415,7 @@
 <h1>LinearReLU<a class="headerlink" href="#linearrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.LinearReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">LinearReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/linear_relu.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.LinearReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">LinearReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/linear_relu.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.LinearReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>A LinearReLU module fused from Linear and ReLU modules, attached with
 FakeQuantize modules for weight, used in
 quantization aware training.</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.freeze_bn_stats.html b/2.9/generated/torch.ao.nn.intrinsic.qat.freeze_bn_stats.html
index 2745f095fba..20fedbbc59f 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.freeze_bn_stats.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.freeze_bn_stats.html
@@ -4415,7 +4415,7 @@
 <h1>freeze_bn_stats<a class="headerlink" href="#freeze-bn-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.freeze_bn_stats">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">freeze_bn_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L1055"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.freeze_bn_stats" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">freeze_bn_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L1055"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.freeze_bn_stats" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.qat.update_bn_stats.html b/2.9/generated/torch.ao.nn.intrinsic.qat.update_bn_stats.html
index 18a6c9e13f8..c21e749f42e 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.qat.update_bn_stats.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.qat.update_bn_stats.html
@@ -4415,7 +4415,7 @@
 <h1>update_bn_stats<a class="headerlink" href="#update-bn-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.qat.update_bn_stats">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">update_bn_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.update_bn_stats" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.qat.</span></span><span class="sig-name descname"><span class="pre">update_bn_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/qat/modules/conv_fused.py#L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.qat.update_bn_stats" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.quantized.BNReLU2d.html b/2.9/generated/torch.ao.nn.intrinsic.quantized.BNReLU2d.html
index 1398421ec63..8547d7ba012 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.quantized.BNReLU2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.quantized.BNReLU2d.html
@@ -4415,7 +4415,7 @@
 <h1>BNReLU2d<a class="headerlink" href="#bnrelu2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.quantized.BNReLU2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">BNReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/quantized/modules/bn_relu.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.BNReLU2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">BNReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/quantized/modules/bn_relu.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.BNReLU2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A BNReLU2d module is a fused module of BatchNorm2d and ReLU</p>
 <p>We adopt the same interface as <a class="reference internal" href="torch.ao.nn.quantized.BatchNorm2d.html#torch.ao.nn.quantized.BatchNorm2d" title="torch.ao.nn.quantized.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.ao.nn.quantized.BatchNorm2d</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.nn.intrinsic.quantized.BNReLU3d.html b/2.9/generated/torch.ao.nn.intrinsic.quantized.BNReLU3d.html
index 5e9579f30c1..ffd0677a629 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.quantized.BNReLU3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.quantized.BNReLU3d.html
@@ -4415,7 +4415,7 @@
 <h1>BNReLU3d<a class="headerlink" href="#bnrelu3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.quantized.BNReLU3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">BNReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/quantized/modules/bn_relu.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.BNReLU3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">BNReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/quantized/modules/bn_relu.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.BNReLU3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A BNReLU3d module is a fused module of BatchNorm3d and ReLU</p>
 <p>We adopt the same interface as <a class="reference internal" href="torch.ao.nn.quantized.BatchNorm3d.html#torch.ao.nn.quantized.BatchNorm3d" title="torch.ao.nn.quantized.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.ao.nn.quantized.BatchNorm3d</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU1d.html b/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU1d.html
index 2b089afe808..ea7cbb718f2 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU1d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvReLU1d<a class="headerlink" href="#convrelu1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.quantized.ConvReLU1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvReLU1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/quantized/modules/conv_relu.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.ConvReLU1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvReLU1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/quantized/modules/conv_relu.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.ConvReLU1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvReLU1d module is a fused module of Conv1d and ReLU</p>
 <p>We adopt the same interface as <a class="reference internal" href="torch.ao.nn.quantized.Conv1d.html#torch.ao.nn.quantized.Conv1d" title="torch.ao.nn.quantized.Conv1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.ao.nn.quantized.Conv1d</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU2d.html b/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU2d.html
index 41a77897400..371aae39ce1 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU2d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvReLU2d<a class="headerlink" href="#convrelu2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.quantized.ConvReLU2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/quantized/modules/conv_relu.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.ConvReLU2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvReLU2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/quantized/modules/conv_relu.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.ConvReLU2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvReLU2d module is a fused module of Conv2d and ReLU</p>
 <p>We adopt the same interface as <a class="reference internal" href="torch.ao.nn.quantized.Conv2d.html#torch.ao.nn.quantized.Conv2d" title="torch.ao.nn.quantized.Conv2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.ao.nn.quantized.Conv2d</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU3d.html b/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU3d.html
index 8e386953df2..28013bac0ba 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU3d.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.quantized.ConvReLU3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvReLU3d<a class="headerlink" href="#convrelu3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.quantized.ConvReLU3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/quantized/modules/conv_relu.py#L186"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.ConvReLU3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvReLU3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/quantized/modules/conv_relu.py#L186"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.ConvReLU3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A ConvReLU3d module is a fused module of Conv3d and ReLU</p>
 <p>We adopt the same interface as <a class="reference internal" href="torch.ao.nn.quantized.Conv3d.html#torch.ao.nn.quantized.Conv3d" title="torch.ao.nn.quantized.Conv3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.ao.nn.quantized.Conv3d</span></code></a>.</p>
 <p>Attributes: Same as torch.ao.nn.quantized.Conv3d</p>
diff --git a/2.9/generated/torch.ao.nn.intrinsic.quantized.LinearReLU.html b/2.9/generated/torch.ao.nn.intrinsic.quantized.LinearReLU.html
index a5fbe40807c..88ef0721caf 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.quantized.LinearReLU.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.quantized.LinearReLU.html
@@ -4415,7 +4415,7 @@
 <h1>LinearReLU<a class="headerlink" href="#linearrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.quantized.LinearReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">LinearReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/quantized/modules/linear_relu.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.LinearReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.</span></span><span class="sig-name descname"><span class="pre">LinearReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/quantized/modules/linear_relu.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.LinearReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>A LinearReLU module fused from Linear and ReLU modules</p>
 <p>We adopt the same interface as <a class="reference internal" href="torch.ao.nn.quantized.Linear.html#torch.ao.nn.quantized.Linear" title="torch.ao.nn.quantized.Linear"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.ao.nn.quantized.Linear</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU.html b/2.9/generated/torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU.html
index 106e3b3cb91..0563cb1c3ce 100644
--- a/2.9/generated/torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU.html
+++ b/2.9/generated/torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU.html
@@ -4415,7 +4415,7 @@
 <h1>LinearReLU<a class="headerlink" href="#linearrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">LinearReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/intrinsic/quantized/dynamic/modules/linear_relu.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.intrinsic.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">LinearReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/intrinsic/quantized/dynamic/modules/linear_relu.py#L12"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.intrinsic.quantized.dynamic.LinearReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>A LinearReLU module fused from Linear and ReLU modules that can be used
 for dynamic quantization.
 Supports both, FP16 and INT8 quantization.</p>
diff --git a/2.9/generated/torch.ao.nn.qat.Conv2d.html b/2.9/generated/torch.ao.nn.qat.Conv2d.html
index 2826f3b27ee..07e50588405 100644
--- a/2.9/generated/torch.ao.nn.qat.Conv2d.html
+++ b/2.9/generated/torch.ao.nn.qat.Conv2d.html
@@ -4415,7 +4415,7 @@
 <h1>Conv2d<a class="headerlink" href="#conv2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.qat.Conv2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.qat.</span></span><span class="sig-name descname"><span class="pre">Conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/qat/modules/conv.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.Conv2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.qat.</span></span><span class="sig-name descname"><span class="pre">Conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/qat/modules/conv.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.Conv2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A Conv2d module attached with FakeQuantize modules for weight,
 used for quantization aware training.</p>
 <p>We adopt the same interface as <cite>torch.nn.Conv2d</cite>, please see
diff --git a/2.9/generated/torch.ao.nn.qat.Conv3d.html b/2.9/generated/torch.ao.nn.qat.Conv3d.html
index 7b559be9ee6..8a331528605 100644
--- a/2.9/generated/torch.ao.nn.qat.Conv3d.html
+++ b/2.9/generated/torch.ao.nn.qat.Conv3d.html
@@ -4415,7 +4415,7 @@
 <h1>Conv3d<a class="headerlink" href="#conv3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.qat.Conv3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.qat.</span></span><span class="sig-name descname"><span class="pre">Conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/qat/modules/conv.py#L249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.Conv3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.qat.</span></span><span class="sig-name descname"><span class="pre">Conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/qat/modules/conv.py#L249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.Conv3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A Conv3d module attached with FakeQuantize modules for weight,
 used for quantization aware training.</p>
 <p>We adopt the same interface as <cite>torch.nn.Conv3d</cite>, please see
diff --git a/2.9/generated/torch.ao.nn.qat.Linear.html b/2.9/generated/torch.ao.nn.qat.Linear.html
index 075c8a639c3..7fd21c538db 100644
--- a/2.9/generated/torch.ao.nn.qat.Linear.html
+++ b/2.9/generated/torch.ao.nn.qat.Linear.html
@@ -4415,7 +4415,7 @@
 <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.qat.Linear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.qat.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/qat/modules/linear.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.Linear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.qat.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/qat/modules/linear.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.Linear" title="Permalink to this definition">#</a></dt>
 <dd><p>A linear module attached with FakeQuantize modules for weight,
 used for quantization aware training.</p>
 <p>We adopt the same interface as <cite>torch.nn.Linear</cite>, please see
@@ -4430,7 +4430,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.qat.Linear.from_float">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/qat/modules/linear.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.Linear.from_float" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/qat/modules/linear.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.Linear.from_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a qat module from a float module or qparams_dict
 Args: <cite>mod</cite> a float module, either produced by torch.ao.quantization utilities
 or directly from user</p>
diff --git a/2.9/generated/torch.ao.nn.qat.dynamic.Linear.html b/2.9/generated/torch.ao.nn.qat.dynamic.Linear.html
index c9814701e4c..8c00134d3f5 100644
--- a/2.9/generated/torch.ao.nn.qat.dynamic.Linear.html
+++ b/2.9/generated/torch.ao.nn.qat.dynamic.Linear.html
@@ -4415,7 +4415,7 @@
 <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.qat.dynamic.Linear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.qat.dynamic.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/qat/dynamic/modules/linear.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.dynamic.Linear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.qat.dynamic.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/qat/dynamic/modules/linear.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.qat.dynamic.Linear" title="Permalink to this definition">#</a></dt>
 <dd><p>A linear module attached with FakeQuantize modules for weight,
 used for dynamic quantization aware training.</p>
 <p>We adopt the same interface as <cite>torch.nn.Linear</cite>, please see
diff --git a/2.9/generated/torch.ao.nn.quantizable.LSTM.html b/2.9/generated/torch.ao.nn.quantizable.LSTM.html
index 26f53226050..f14890ec4ad 100644
--- a/2.9/generated/torch.ao.nn.quantizable.LSTM.html
+++ b/2.9/generated/torch.ao.nn.quantizable.LSTM.html
@@ -4415,7 +4415,7 @@
 <h1>LSTM<a class="headerlink" href="#lstm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantizable.LSTM">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantizable.</span></span><span class="sig-name descname"><span class="pre">LSTM</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_gates</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantizable/modules/rnn.py#L400"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantizable.LSTM" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantizable.</span></span><span class="sig-name descname"><span class="pre">LSTM</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_gates</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantizable/modules/rnn.py#L400"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantizable.LSTM" title="Permalink to this definition">#</a></dt>
 <dd><p>A quantizable long short-term memory (LSTM).</p>
 <p>For the description and the argument types, please, refer to <a class="reference internal" href="torch.nn.LSTM.html#torch.nn.LSTM" title="torch.nn.LSTM"><code class="xref py py-class docutils literal notranslate"><span class="pre">LSTM</span></code></a></p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.nn.quantizable.MultiheadAttention.html b/2.9/generated/torch.ao.nn.quantizable.MultiheadAttention.html
index c5a28d7c9d0..8f233209a20 100644
--- a/2.9/generated/torch.ao.nn.quantizable.MultiheadAttention.html
+++ b/2.9/generated/torch.ao.nn.quantizable.MultiheadAttention.html
@@ -4415,12 +4415,12 @@
 <h1>MultiheadAttention<a class="headerlink" href="#multiheadattention" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantizable.MultiheadAttention">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantizable.</span></span><span class="sig-name descname"><span class="pre">MultiheadAttention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embed_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_heads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_bias_kv</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_zero_attn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantizable/modules/activation.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantizable.MultiheadAttention" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantizable.</span></span><span class="sig-name descname"><span class="pre">MultiheadAttention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embed_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_heads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_bias_kv</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_zero_attn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantizable/modules/activation.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantizable.MultiheadAttention" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantizable.MultiheadAttention.dequantize">
-<span class="sig-name descname"><span class="pre">dequantize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantizable/modules/activation.py#L191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantizable.MultiheadAttention.dequantize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">dequantize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantizable/modules/activation.py#L191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantizable.MultiheadAttention.dequantize" title="Permalink to this definition">#</a></dt>
 <dd><p>Utility to convert the quantized MHA back to float.</p>
 <p>The motivation for this is that it is not trivial to convert the weights
 from the format that is used in the quantized version back to the
@@ -4429,7 +4429,7 @@ <h1>MultiheadAttention<a class="headerlink" href="#multiheadattention" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantizable.MultiheadAttention.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">need_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">average_attn_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantizable/modules/activation.py#L278"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantizable.MultiheadAttention.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">need_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">average_attn_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantizable/modules/activation.py#L278"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantizable.MultiheadAttention.forward" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Note::</dt><dd><p>Please, refer to <a class="reference internal" href="torch.nn.MultiheadAttention.html#torch.nn.MultiheadAttention.forward" title="torch.nn.MultiheadAttention.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> for more
 information</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.BatchNorm2d.html b/2.9/generated/torch.ao.nn.quantized.BatchNorm2d.html
index 4baf1338d25..1bae0569921 100644
--- a/2.9/generated/torch.ao.nn.quantized.BatchNorm2d.html
+++ b/2.9/generated/torch.ao.nn.quantized.BatchNorm2d.html
@@ -4415,7 +4415,7 @@
 <h1>BatchNorm2d<a class="headerlink" href="#batchnorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.BatchNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">BatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/batchnorm.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.BatchNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">BatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/batchnorm.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.BatchNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.BatchNorm2d.html#torch.nn.BatchNorm2d" title="torch.nn.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm2d</span></code></a>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.ao.nn.quantized.BatchNorm3d.html b/2.9/generated/torch.ao.nn.quantized.BatchNorm3d.html
index c158dd7f9ca..e15e97a5156 100644
--- a/2.9/generated/torch.ao.nn.quantized.BatchNorm3d.html
+++ b/2.9/generated/torch.ao.nn.quantized.BatchNorm3d.html
@@ -4415,7 +4415,7 @@
 <h1>BatchNorm3d<a class="headerlink" href="#batchnorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.BatchNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">BatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/batchnorm.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.BatchNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">BatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/batchnorm.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.BatchNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.BatchNorm3d.html#torch.nn.BatchNorm3d" title="torch.nn.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm3d</span></code></a>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.ao.nn.quantized.Conv1d.html b/2.9/generated/torch.ao.nn.quantized.Conv1d.html
index e7a539ed2e9..aee50fd1fe9 100644
--- a/2.9/generated/torch.ao.nn.quantized.Conv1d.html
+++ b/2.9/generated/torch.ao.nn.quantized.Conv1d.html
@@ -4415,7 +4415,7 @@
 <h1>Conv1d<a class="headerlink" href="#conv1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Conv1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Conv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Conv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D convolution over a quantized input signal composed of
 several quantized input planes.</p>
 <p>For details on input arguments, parameters, and implementation see
@@ -4450,7 +4450,7 @@ <h1>Conv1d<a class="headerlink" href="#conv1d" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Conv1d.from_float">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L469"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv1d.from_float" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L469"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv1d.from_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a quantized module from a float module or qparams_dict.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.Conv2d.html b/2.9/generated/torch.ao.nn.quantized.Conv2d.html
index 0538efb4867..f25870088d8 100644
--- a/2.9/generated/torch.ao.nn.quantized.Conv2d.html
+++ b/2.9/generated/torch.ao.nn.quantized.Conv2d.html
@@ -4415,7 +4415,7 @@
 <h1>Conv2d<a class="headerlink" href="#conv2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Conv2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L482"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L482"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D convolution over a quantized input signal composed of
 several quantized input planes.</p>
 <p>For details on input arguments, parameters, and implementation see
@@ -4454,7 +4454,7 @@ <h1>Conv2d<a class="headerlink" href="#conv2d" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Conv2d.from_float">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L599"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv2d.from_float" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L599"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv2d.from_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a quantized module from a float module or qparams_dict.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.Conv3d.html b/2.9/generated/torch.ao.nn.quantized.Conv3d.html
index 07d5f0758e0..4bf11f1699b 100644
--- a/2.9/generated/torch.ao.nn.quantized.Conv3d.html
+++ b/2.9/generated/torch.ao.nn.quantized.Conv3d.html
@@ -4415,7 +4415,7 @@
 <h1>Conv3d<a class="headerlink" href="#conv3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Conv3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D convolution over a quantized input signal composed of
 several quantized input planes.</p>
 <p>For details on input arguments, parameters, and implementation see
@@ -4454,7 +4454,7 @@ <h1>Conv3d<a class="headerlink" href="#conv3d" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Conv3d.from_float">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L730"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv3d.from_float" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L730"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Conv3d.from_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a quantized module from a float module or qparams_dict.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.ConvTranspose1d.html b/2.9/generated/torch.ao.nn.quantized.ConvTranspose1d.html
index 186cbf8e7ea..ce0b1f48657 100644
--- a/2.9/generated/torch.ao.nn.quantized.ConvTranspose1d.html
+++ b/2.9/generated/torch.ao.nn.quantized.ConvTranspose1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvTranspose1d<a class="headerlink" href="#convtranspose1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.ConvTranspose1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L873"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ConvTranspose1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L873"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ConvTranspose1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D transposed convolution operator over an input image
 composed of several input planes.
 For details on input arguments, parameters, and implementation see
diff --git a/2.9/generated/torch.ao.nn.quantized.ConvTranspose2d.html b/2.9/generated/torch.ao.nn.quantized.ConvTranspose2d.html
index adf6b8b3272..f97e9a45ad5 100644
--- a/2.9/generated/torch.ao.nn.quantized.ConvTranspose2d.html
+++ b/2.9/generated/torch.ao.nn.quantized.ConvTranspose2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvTranspose2d<a class="headerlink" href="#convtranspose2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.ConvTranspose2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L998"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ConvTranspose2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L998"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ConvTranspose2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D transposed convolution operator over an input image
 composed of several input planes.
 For details on input arguments, parameters, and implementation see
diff --git a/2.9/generated/torch.ao.nn.quantized.ConvTranspose3d.html b/2.9/generated/torch.ao.nn.quantized.ConvTranspose3d.html
index 9b742515ae9..14fd5fce0ae 100644
--- a/2.9/generated/torch.ao.nn.quantized.ConvTranspose3d.html
+++ b/2.9/generated/torch.ao.nn.quantized.ConvTranspose3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvTranspose3d<a class="headerlink" href="#convtranspose3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.ConvTranspose3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/conv.py#L1121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ConvTranspose3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/conv.py#L1121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ConvTranspose3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D transposed convolution operator over an input image
 composed of several input planes.
 For details on input arguments, parameters, and implementation see
diff --git a/2.9/generated/torch.ao.nn.quantized.ELU.html b/2.9/generated/torch.ao.nn.quantized.ELU.html
index db79be9cfcc..ed3cdb29ece 100644
--- a/2.9/generated/torch.ao.nn.quantized.ELU.html
+++ b/2.9/generated/torch.ao.nn.quantized.ELU.html
@@ -4415,7 +4415,7 @@
 <h1>ELU<a class="headerlink" href="#elu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.ELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/activation.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/activation.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ELU" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized equivalent of <a class="reference internal" href="torch.nn.ELU.html#torch.nn.ELU" title="torch.nn.ELU"><code class="xref py py-class docutils literal notranslate"><span class="pre">ELU</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.Embedding.html b/2.9/generated/torch.ao.nn.quantized.Embedding.html
index 9488e4879dd..a00df6e1914 100644
--- a/2.9/generated/torch.ao.nn.quantized.Embedding.html
+++ b/2.9/generated/torch.ao.nn.quantized.Embedding.html
@@ -4415,7 +4415,7 @@
 <h1>Embedding<a class="headerlink" href="#embedding" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Embedding">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/embedding_ops.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Embedding" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/embedding_ops.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Embedding" title="Permalink to this definition">#</a></dt>
 <dd><p>A quantized Embedding module with quantized packed weights as inputs.
 We adopt the same interface as <cite>torch.nn.Embedding</cite>, please see
 <a class="reference external" href="https://pytorch.org/docs/stable/generated/torch.nn.Embedding.html">https://pytorch.org/docs/stable/generated/torch.nn.Embedding.html</a> for documentation.</p>
@@ -4439,7 +4439,7 @@ <h1>Embedding<a class="headerlink" href="#embedding" title="Permalink to this he
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Embedding.from_float">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/embedding_ops.py#L190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Embedding.from_float" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/embedding_ops.py#L190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Embedding.from_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a quantized embedding module from a float module</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.EmbeddingBag.html b/2.9/generated/torch.ao.nn.quantized.EmbeddingBag.html
index 7cb42d2ca8e..ffeb8988c57 100644
--- a/2.9/generated/torch.ao.nn.quantized.EmbeddingBag.html
+++ b/2.9/generated/torch.ao.nn.quantized.EmbeddingBag.html
@@ -4415,7 +4415,7 @@
 <h1>EmbeddingBag<a class="headerlink" href="#embeddingbag" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.EmbeddingBag">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">EmbeddingBag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'sum'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/embedding_ops.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.EmbeddingBag" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">EmbeddingBag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'sum'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/embedding_ops.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.EmbeddingBag" title="Permalink to this definition">#</a></dt>
 <dd><p>A quantized EmbeddingBag module with quantized packed weights as inputs.
 We adopt the same interface as <cite>torch.nn.EmbeddingBag</cite>, please see
 <a class="reference external" href="https://pytorch.org/docs/stable/generated/torch.nn.EmbeddingBag.html">https://pytorch.org/docs/stable/generated/torch.nn.EmbeddingBag.html</a> for documentation.</p>
@@ -4440,7 +4440,7 @@ <h1>EmbeddingBag<a class="headerlink" href="#embeddingbag" title="Permalink to t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.EmbeddingBag.from_float">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/embedding_ops.py#L341"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.EmbeddingBag.from_float" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/embedding_ops.py#L341"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.EmbeddingBag.from_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a quantized embedding_bag module from a float module</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.FXFloatFunctional.html b/2.9/generated/torch.ao.nn.quantized.FXFloatFunctional.html
index 0b662a56383..3162d1ea063 100644
--- a/2.9/generated/torch.ao.nn.quantized.FXFloatFunctional.html
+++ b/2.9/generated/torch.ao.nn.quantized.FXFloatFunctional.html
@@ -4415,7 +4415,7 @@
 <h1>FXFloatFunctional<a class="headerlink" href="#fxfloatfunctional" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.FXFloatFunctional">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">FXFloatFunctional</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/functional_modules.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.FXFloatFunctional" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">FXFloatFunctional</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/functional_modules.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.FXFloatFunctional" title="Permalink to this definition">#</a></dt>
 <dd><p>module to replace FloatFunctional module before FX graph mode quantization,
 since activation_post_process will be inserted in top level module directly</p>
 <dl class="simple">
diff --git a/2.9/generated/torch.ao.nn.quantized.FloatFunctional.html b/2.9/generated/torch.ao.nn.quantized.FloatFunctional.html
index 97c3c7ad4c1..44987e45bba 100644
--- a/2.9/generated/torch.ao.nn.quantized.FloatFunctional.html
+++ b/2.9/generated/torch.ao.nn.quantized.FloatFunctional.html
@@ -4415,7 +4415,7 @@
 <h1>FloatFunctional<a class="headerlink" href="#floatfunctional" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.FloatFunctional">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">FloatFunctional</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/functional_modules.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.FloatFunctional" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">FloatFunctional</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/functional_modules.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.FloatFunctional" title="Permalink to this definition">#</a></dt>
 <dd><p>State collector class for float operations.</p>
 <p>The instance of this class can be used instead of the <code class="docutils literal notranslate"><span class="pre">torch.</span></code> prefix for
 some operations. See example usage below.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.GroupNorm.html b/2.9/generated/torch.ao.nn.quantized.GroupNorm.html
index 126f6a9ac12..4399a0c2ada 100644
--- a/2.9/generated/torch.ao.nn.quantized.GroupNorm.html
+++ b/2.9/generated/torch.ao.nn.quantized.GroupNorm.html
@@ -4415,7 +4415,7 @@
 <h1>GroupNorm<a class="headerlink" href="#groupnorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.GroupNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">GroupNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_groups</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/normalization.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.GroupNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">GroupNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_groups</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/normalization.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.GroupNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.GroupNorm.html#torch.nn.GroupNorm" title="torch.nn.GroupNorm"><code class="xref py py-class docutils literal notranslate"><span class="pre">GroupNorm</span></code></a>.</p>
 <dl class="simple">
 <dt>Additional args:</dt><dd><ul class="simple">
diff --git a/2.9/generated/torch.ao.nn.quantized.Hardswish.html b/2.9/generated/torch.ao.nn.quantized.Hardswish.html
index 444863cfdb3..594ed031047 100644
--- a/2.9/generated/torch.ao.nn.quantized.Hardswish.html
+++ b/2.9/generated/torch.ao.nn.quantized.Hardswish.html
@@ -4415,7 +4415,7 @@
 <h1>Hardswish<a class="headerlink" href="#hardswish" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Hardswish">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/activation.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Hardswish" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/activation.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Hardswish" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.Hardswish.html#torch.nn.Hardswish" title="torch.nn.Hardswish"><code class="xref py py-class docutils literal notranslate"><span class="pre">Hardswish</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.InstanceNorm1d.html b/2.9/generated/torch.ao.nn.quantized.InstanceNorm1d.html
index 36e09a06c39..2d3ae053c55 100644
--- a/2.9/generated/torch.ao.nn.quantized.InstanceNorm1d.html
+++ b/2.9/generated/torch.ao.nn.quantized.InstanceNorm1d.html
@@ -4415,7 +4415,7 @@
 <h1>InstanceNorm1d<a class="headerlink" href="#instancenorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.InstanceNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/normalization.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.InstanceNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/normalization.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.InstanceNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.InstanceNorm1d.html#torch.nn.InstanceNorm1d" title="torch.nn.InstanceNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm1d</span></code></a>.</p>
 <dl class="simple">
 <dt>Additional args:</dt><dd><ul class="simple">
diff --git a/2.9/generated/torch.ao.nn.quantized.InstanceNorm2d.html b/2.9/generated/torch.ao.nn.quantized.InstanceNorm2d.html
index a47f2d07ebf..d0f8f1502fc 100644
--- a/2.9/generated/torch.ao.nn.quantized.InstanceNorm2d.html
+++ b/2.9/generated/torch.ao.nn.quantized.InstanceNorm2d.html
@@ -4415,7 +4415,7 @@
 <h1>InstanceNorm2d<a class="headerlink" href="#instancenorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.InstanceNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/normalization.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.InstanceNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/normalization.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.InstanceNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.InstanceNorm2d.html#torch.nn.InstanceNorm2d" title="torch.nn.InstanceNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm2d</span></code></a>.</p>
 <dl class="simple">
 <dt>Additional args:</dt><dd><ul class="simple">
diff --git a/2.9/generated/torch.ao.nn.quantized.InstanceNorm3d.html b/2.9/generated/torch.ao.nn.quantized.InstanceNorm3d.html
index 6269173742e..9f1a0cefa60 100644
--- a/2.9/generated/torch.ao.nn.quantized.InstanceNorm3d.html
+++ b/2.9/generated/torch.ao.nn.quantized.InstanceNorm3d.html
@@ -4415,7 +4415,7 @@
 <h1>InstanceNorm3d<a class="headerlink" href="#instancenorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.InstanceNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/normalization.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.InstanceNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/normalization.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.InstanceNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.InstanceNorm3d.html#torch.nn.InstanceNorm3d" title="torch.nn.InstanceNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm3d</span></code></a>.</p>
 <dl class="simple">
 <dt>Additional args:</dt><dd><ul class="simple">
diff --git a/2.9/generated/torch.ao.nn.quantized.LayerNorm.html b/2.9/generated/torch.ao.nn.quantized.LayerNorm.html
index 454186e9664..cdaefed1104 100644
--- a/2.9/generated/torch.ao.nn.quantized.LayerNorm.html
+++ b/2.9/generated/torch.ao.nn.quantized.LayerNorm.html
@@ -4415,7 +4415,7 @@
 <h1>LayerNorm<a class="headerlink" href="#layernorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.LayerNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">LayerNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/normalization.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.LayerNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">LayerNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/normalization.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.LayerNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.LayerNorm.html#torch.nn.LayerNorm" title="torch.nn.LayerNorm"><code class="xref py py-class docutils literal notranslate"><span class="pre">LayerNorm</span></code></a>.</p>
 <dl class="simple">
 <dt>Additional args:</dt><dd><ul class="simple">
diff --git a/2.9/generated/torch.ao.nn.quantized.LeakyReLU.html b/2.9/generated/torch.ao.nn.quantized.LeakyReLU.html
index 509f3257111..e02d8e5fb1a 100644
--- a/2.9/generated/torch.ao.nn.quantized.LeakyReLU.html
+++ b/2.9/generated/torch.ao.nn.quantized.LeakyReLU.html
@@ -4415,7 +4415,7 @@
 <h1>LeakyReLU<a class="headerlink" href="#leakyrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.LeakyReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">LeakyReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/activation.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.LeakyReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">LeakyReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/activation.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.LeakyReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized equivalent of <a class="reference internal" href="torch.nn.LeakyReLU.html#torch.nn.LeakyReLU" title="torch.nn.LeakyReLU"><code class="xref py py-class docutils literal notranslate"><span class="pre">LeakyReLU</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.Linear.html b/2.9/generated/torch.ao.nn.quantized.Linear.html
index 130777c141f..90c2c7bf498 100644
--- a/2.9/generated/torch.ao.nn.quantized.Linear.html
+++ b/2.9/generated/torch.ao.nn.quantized.Linear.html
@@ -4415,7 +4415,7 @@
 <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Linear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias_</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/linear.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Linear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias_</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/linear.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Linear" title="Permalink to this definition">#</a></dt>
 <dd><p>A quantized linear module with quantized tensor as inputs and outputs.
 We adopt the same interface as <cite>torch.nn.Linear</cite>, please see
 <a class="reference external" href="https://pytorch.org/docs/stable/nn.html#torch.nn.Linear">https://pytorch.org/docs/stable/nn.html#torch.nn.Linear</a> for documentation.</p>
@@ -4444,7 +4444,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Linear.from_float">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/linear.py#L285"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Linear.from_float" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/linear.py#L285"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Linear.from_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a quantized module from an observed float module</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4460,7 +4460,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Linear.from_reference">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_reference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ref_qlinear</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_zero_point</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/linear.py#L347"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Linear.from_reference" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_reference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ref_qlinear</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_zero_point</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/linear.py#L347"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Linear.from_reference" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a (fbgemm/qnnpack) quantized module from a reference quantized module</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.QFunctional.html b/2.9/generated/torch.ao.nn.quantized.QFunctional.html
index 92ab3f9aa6f..802f4c121e0 100644
--- a/2.9/generated/torch.ao.nn.quantized.QFunctional.html
+++ b/2.9/generated/torch.ao.nn.quantized.QFunctional.html
@@ -4415,7 +4415,7 @@
 <h1>QFunctional<a class="headerlink" href="#qfunctional" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.QFunctional">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">QFunctional</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/functional_modules.py#L164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.QFunctional" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">QFunctional</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/functional_modules.py#L164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.QFunctional" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper class for quantized operations.</p>
 <p>The instance of this class can be used instead of the
 <code class="docutils literal notranslate"><span class="pre">torch.ops.quantized</span></code> prefix. See example usage below.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.ReLU6.html b/2.9/generated/torch.ao.nn.quantized.ReLU6.html
index dc9a56cf179..29de80d6cd7 100644
--- a/2.9/generated/torch.ao.nn.quantized.ReLU6.html
+++ b/2.9/generated/torch.ao.nn.quantized.ReLU6.html
@@ -4415,7 +4415,7 @@
 <h1>ReLU6<a class="headerlink" href="#relu6" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.ReLU6">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ReLU6</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/activation.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ReLU6" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">ReLU6</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/activation.py#L19"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.ReLU6" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise function:</p>
 <p><span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>ReLU6</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>x</mi><mn>0</mn></msub><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo separator="true">,</mo><mi>q</mi><mo stretchy="false">(</mo><mn>6</mn><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{ReLU6}(x) = \min(\max(x_0, x), q(6))</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">ReLU6</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">min</span><span class="mopen">(</span><span class="mop">max</span><span class="mopen">(</span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">0</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">q</span><span class="mopen">(</span><span class="mord">6</span><span class="mclose">))</span></span></span></span></span>, where <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>0</mn></msub></mrow><annotation encoding="application/x-tex">x_0</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">0</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> is the
 zero_point, and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>q</mi><mo stretchy="false">(</mo><mn>6</mn><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">q(6)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">q</span><span class="mopen">(</span><span class="mord">6</span><span class="mclose">)</span></span></span></span></span> is the quantized representation of number 6.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.Sigmoid.html b/2.9/generated/torch.ao.nn.quantized.Sigmoid.html
index 80de2e351c1..6a624de6c84 100644
--- a/2.9/generated/torch.ao.nn.quantized.Sigmoid.html
+++ b/2.9/generated/torch.ao.nn.quantized.Sigmoid.html
@@ -4415,7 +4415,7 @@
 <h1>Sigmoid<a class="headerlink" href="#sigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.Sigmoid">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Sigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_zero_point</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/modules/activation.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Sigmoid" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.</span></span><span class="sig-name descname"><span class="pre">Sigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_zero_point</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/modules/activation.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.Sigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized equivalent of <a class="reference internal" href="torch.nn.Sigmoid.html#torch.nn.Sigmoid" title="torch.nn.Sigmoid"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sigmoid</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.dynamic.GRU.html b/2.9/generated/torch.ao.nn.quantized.dynamic.GRU.html
index f12a4f3d41a..4da42c95164 100644
--- a/2.9/generated/torch.ao.nn.quantized.dynamic.GRU.html
+++ b/2.9/generated/torch.ao.nn.quantized.dynamic.GRU.html
@@ -4415,7 +4415,7 @@
 <h1>GRU<a class="headerlink" href="#gru" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.dynamic.GRU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">GRU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/dynamic/modules/rnn.py#L683"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.GRU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">GRU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/dynamic/modules/rnn.py#L683"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.GRU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a multi-layer gated recurrent unit (GRU) RNN to an input sequence.</p>
 <p>For each element in the input sequence, each layer computes the following
 function:</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.dynamic.GRUCell.html b/2.9/generated/torch.ao.nn.quantized.dynamic.GRUCell.html
index 6875f36b700..ae9907ba488 100644
--- a/2.9/generated/torch.ao.nn.quantized.dynamic.GRUCell.html
+++ b/2.9/generated/torch.ao.nn.quantized.dynamic.GRUCell.html
@@ -4415,7 +4415,7 @@
 <h1>GRUCell<a class="headerlink" href="#grucell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.dynamic.GRUCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">GRUCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/dynamic/modules/rnn.py#L1318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.GRUCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">GRUCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/dynamic/modules/rnn.py#L1318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.GRUCell" title="Permalink to this definition">#</a></dt>
 <dd><p>A gated recurrent unit (GRU) cell</p>
 <p>A dynamic quantized GRUCell module with floating point tensor as inputs and outputs.
 Weights are quantized to 8 bits. We adopt the same interface as <cite>torch.nn.GRUCell</cite>,
diff --git a/2.9/generated/torch.ao.nn.quantized.dynamic.LSTM.html b/2.9/generated/torch.ao.nn.quantized.dynamic.LSTM.html
index e47162f33ee..5de6499dbb7 100644
--- a/2.9/generated/torch.ao.nn.quantized.dynamic.LSTM.html
+++ b/2.9/generated/torch.ao.nn.quantized.dynamic.LSTM.html
@@ -4415,7 +4415,7 @@
 <h1>LSTM<a class="headerlink" href="#lstm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.dynamic.LSTM">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">LSTM</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/dynamic/modules/rnn.py#L508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.LSTM" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">LSTM</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/dynamic/modules/rnn.py#L508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.LSTM" title="Permalink to this definition">#</a></dt>
 <dd><p>A dynamic quantized LSTM module with floating point tensor as inputs and outputs.
 We adopt the same interface as <cite>torch.nn.LSTM</cite>, please see
 <a class="reference external" href="https://pytorch.org/docs/stable/nn.html#torch.nn.LSTM">https://pytorch.org/docs/stable/nn.html#torch.nn.LSTM</a> for documentation.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.dynamic.LSTMCell.html b/2.9/generated/torch.ao.nn.quantized.dynamic.LSTMCell.html
index 5860cb743e4..325f8ff4db3 100644
--- a/2.9/generated/torch.ao.nn.quantized.dynamic.LSTMCell.html
+++ b/2.9/generated/torch.ao.nn.quantized.dynamic.LSTMCell.html
@@ -4415,7 +4415,7 @@
 <h1>LSTMCell<a class="headerlink" href="#lstmcell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.dynamic.LSTMCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">LSTMCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/dynamic/modules/rnn.py#L1265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.LSTMCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">LSTMCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/dynamic/modules/rnn.py#L1265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.LSTMCell" title="Permalink to this definition">#</a></dt>
 <dd><p>A long short-term memory (LSTM) cell.</p>
 <p>A dynamic quantized LSTMCell module with floating point tensor as inputs and outputs.
 Weights are quantized to 8 bits. We adopt the same interface as <cite>torch.nn.LSTMCell</cite>,
diff --git a/2.9/generated/torch.ao.nn.quantized.dynamic.Linear.html b/2.9/generated/torch.ao.nn.quantized.dynamic.Linear.html
index a8cbcf1cdd0..501fc456055 100644
--- a/2.9/generated/torch.ao.nn.quantized.dynamic.Linear.html
+++ b/2.9/generated/torch.ao.nn.quantized.dynamic.Linear.html
@@ -4415,7 +4415,7 @@
 <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.dynamic.Linear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias_</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/dynamic/modules/linear.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.Linear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias_</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/dynamic/modules/linear.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.Linear" title="Permalink to this definition">#</a></dt>
 <dd><p>A dynamic quantized linear module with floating point tensor as inputs and outputs.
 We adopt the same interface as <cite>torch.nn.Linear</cite>, please see
 <a class="reference external" href="https://pytorch.org/docs/stable/nn.html#torch.nn.Linear">https://pytorch.org/docs/stable/nn.html#torch.nn.Linear</a> for documentation.</p>
@@ -4442,7 +4442,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.dynamic.Linear.from_float">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/dynamic/modules/linear.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.Linear.from_float" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/dynamic/modules/linear.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.Linear.from_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a dynamic quantized module from a float module or qparams_dict</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4454,7 +4454,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.dynamic.Linear.from_reference">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_reference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ref_qlinear</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/dynamic/modules/linear.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.Linear.from_reference" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_reference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ref_qlinear</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/dynamic/modules/linear.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.Linear.from_reference" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a (fbgemm/qnnpack) dynamic quantized module from a reference quantized
 module
 :param ref_qlinear: a reference quantized  module, either produced by
diff --git a/2.9/generated/torch.ao.nn.quantized.dynamic.RNNCell.html b/2.9/generated/torch.ao.nn.quantized.dynamic.RNNCell.html
index efc30df4432..720ba335e50 100644
--- a/2.9/generated/torch.ao.nn.quantized.dynamic.RNNCell.html
+++ b/2.9/generated/torch.ao.nn.quantized.dynamic.RNNCell.html
@@ -4415,7 +4415,7 @@
 <h1>RNNCell<a class="headerlink" href="#rnncell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.dynamic.RNNCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">RNNCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/dynamic/modules/rnn.py#L1199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.RNNCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.dynamic.</span></span><span class="sig-name descname"><span class="pre">RNNCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/dynamic/modules/rnn.py#L1199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.dynamic.RNNCell" title="Permalink to this definition">#</a></dt>
 <dd><p>An Elman RNN cell with tanh or ReLU non-linearity.
 A dynamic quantized RNNCell module with floating point tensor as inputs and outputs.
 Weights are quantized to 8 bits. We adopt the same interface as <cite>torch.nn.RNNCell</cite>,
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.adaptive_avg_pool2d.html b/2.9/generated/torch.ao.nn.quantized.functional.adaptive_avg_pool2d.html
index ea1074a05ee..0a6f0096d0b 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.adaptive_avg_pool2d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.adaptive_avg_pool2d.html
@@ -4415,7 +4415,7 @@
 <h1>adaptive_avg_pool2d<a class="headerlink" href="#adaptive-avg-pool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.adaptive_avg_pool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_avg_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.adaptive_avg_pool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_avg_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.adaptive_avg_pool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D adaptive average pooling over a quantized input signal composed
 of several quantized input planes.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.adaptive_avg_pool3d.html b/2.9/generated/torch.ao.nn.quantized.functional.adaptive_avg_pool3d.html
index da64bd6e01a..c0072406161 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.adaptive_avg_pool3d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.adaptive_avg_pool3d.html
@@ -4415,7 +4415,7 @@
 <h1>adaptive_avg_pool3d<a class="headerlink" href="#adaptive-avg-pool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.adaptive_avg_pool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_avg_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.adaptive_avg_pool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_avg_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.adaptive_avg_pool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D adaptive average pooling over a quantized input signal composed
 of several quantized input planes.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.avg_pool2d.html b/2.9/generated/torch.ao.nn.quantized.functional.avg_pool2d.html
index ee7ff683354..6c2127f30e4 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.avg_pool2d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.avg_pool2d.html
@@ -4415,7 +4415,7 @@
 <h1>avg_pool2d<a class="headerlink" href="#avg-pool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.avg_pool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">avg_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.avg_pool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">avg_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L44"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.avg_pool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies 2D average-pooling operation in <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi><mi>H</mi><mo>×</mo><mi>k</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">kH \times kW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span></span></span></span></span> regions by step size
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>s</mi><mi>H</mi><mo>×</mo><mi>s</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">sH \times sW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7667em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">sH</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal">s</span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span></span></span></span></span> steps. The number of output features is equal to the number of
 input planes.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.avg_pool3d.html b/2.9/generated/torch.ao.nn.quantized.functional.avg_pool3d.html
index ee20bfffdeb..9a3d4fe940c 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.avg_pool3d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.avg_pool3d.html
@@ -4415,7 +4415,7 @@
 <h1>avg_pool3d<a class="headerlink" href="#avg-pool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.avg_pool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">avg_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.avg_pool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">avg_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.avg_pool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies 3D average-pooling operation in <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi><mi>D</mi><mtext> </mtext><mi>t</mi><mi>i</mi><mi>m</mi><mi>e</mi><mi>s</mi><mi>k</mi><mi>H</mi><mo>×</mo><mi>k</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">kD \ times kH \times kW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mspace"> </span><span class="mord mathnormal">t</span><span class="mord mathnormal">im</span><span class="mord mathnormal">es</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span></span></span></span></span> regions by step size
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>s</mi><mi>D</mi><mo>×</mo><mi>s</mi><mi>H</mi><mo>×</mo><mi>s</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">sD \times sH \times sW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7667em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">sD</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.7667em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">sH</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal">s</span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span></span></span></span></span> steps. The number of output features is equal to the number of
 input planes.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.celu.html b/2.9/generated/torch.ao.nn.quantized.functional.celu.html
index 4b214e1f893..75e575aca88 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.celu.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.celu.html
@@ -4415,7 +4415,7 @@
 <h1>celu<a class="headerlink" href="#celu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.celu">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">celu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.celu" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">celu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.celu" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the quantized CELU function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>CELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>α</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mi mathvariant="normal">/</mi><mi>α</mi><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{CELU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x / \alpha) - 1))
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.clamp.html b/2.9/generated/torch.ao.nn.quantized.functional.clamp.html
index 58c3344de93..9558a63fb1b 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.clamp.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.clamp.html
@@ -4415,7 +4415,7 @@
 <h1>clamp<a class="headerlink" href="#clamp" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.clamp">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">clamp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.clamp" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">clamp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.clamp" title="Permalink to this definition">#</a></dt>
 <dd><p>float(input, min_, max_) -&gt; Tensor</p>
 <p>Applies the clamp function element-wise.
 See <code class="xref py py-class docutils literal notranslate"><span class="pre">clamp</span></code> for more details.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.conv1d.html b/2.9/generated/torch.ao.nn.quantized.functional.conv1d.html
index 108d8230c13..4e7d93c5f48 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.conv1d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.conv1d.html
@@ -4415,7 +4415,7 @@
 <h1>conv1d<a class="headerlink" href="#conv1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.conv1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">conv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.conv1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">conv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.conv1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D convolution over a quantized 1D input composed of several input
 planes.</p>
 <p>See <a class="reference internal" href="torch.ao.nn.quantized.Conv1d.html#torch.ao.nn.quantized.Conv1d" title="torch.ao.nn.quantized.Conv1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv1d</span></code></a> for details and output shape.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.conv2d.html b/2.9/generated/torch.ao.nn.quantized.functional.conv2d.html
index 8a2a4ee8460..a9c58f3ba23 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.conv2d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.conv2d.html
@@ -4415,7 +4415,7 @@
 <h1>conv2d<a class="headerlink" href="#conv2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.conv2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L246"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.conv2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L246"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.conv2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D convolution over a quantized 2D input composed of several input
 planes.</p>
 <p>See <a class="reference internal" href="torch.ao.nn.quantized.Conv2d.html#torch.ao.nn.quantized.Conv2d" title="torch.ao.nn.quantized.Conv2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv2d</span></code></a> for details and output shape.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.conv3d.html b/2.9/generated/torch.ao.nn.quantized.functional.conv3d.html
index bb48628161f..204f09e48c6 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.conv3d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.conv3d.html
@@ -4415,7 +4415,7 @@
 <h1>conv3d<a class="headerlink" href="#conv3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.conv3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.conv3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.conv3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D convolution over a quantized 3D input composed of several input
 planes.</p>
 <p>See <a class="reference internal" href="torch.ao.nn.quantized.Conv3d.html#torch.ao.nn.quantized.Conv3d" title="torch.ao.nn.quantized.Conv3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv3d</span></code></a> for details and output shape.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.elu.html b/2.9/generated/torch.ao.nn.quantized.functional.elu.html
index 0da89d67cbe..0fe9074d339 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.elu.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.elu.html
@@ -4415,7 +4415,7 @@
 <h1>elu<a class="headerlink" href="#elu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.elu">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">elu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L637"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.elu" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">elu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L637"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.elu" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.functional.elu.html#torch.nn.functional.elu" title="torch.nn.functional.elu"><code class="xref py py-func docutils literal notranslate"><span class="pre">elu()</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.hardsigmoid.html b/2.9/generated/torch.ao.nn.quantized.functional.hardsigmoid.html
index 4abd08fe222..8a408f8c7b7 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.hardsigmoid.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.hardsigmoid.html
@@ -4415,7 +4415,7 @@
 <h1>hardsigmoid<a class="headerlink" href="#hardsigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.hardsigmoid">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">hardsigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L651"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.hardsigmoid" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">hardsigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L651"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.hardsigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.functional.hardsigmoid.html#torch.nn.functional.hardsigmoid" title="torch.nn.functional.hardsigmoid"><code class="xref py py-func docutils literal notranslate"><span class="pre">hardsigmoid()</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.hardswish.html b/2.9/generated/torch.ao.nn.quantized.functional.hardswish.html
index 4605b7fe53a..6ddf3cef892 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.hardswish.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.hardswish.html
@@ -4415,7 +4415,7 @@
 <h1>hardswish<a class="headerlink" href="#hardswish" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.hardswish">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L604"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.hardswish" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L604"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.hardswish" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.functional.hardswish.html#torch.nn.functional.hardswish" title="torch.nn.functional.hardswish"><code class="xref py py-func docutils literal notranslate"><span class="pre">hardswish()</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.hardtanh.html b/2.9/generated/torch.ao.nn.quantized.functional.hardtanh.html
index c8e01fdde1f..a7390248e86 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.hardtanh.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.hardtanh.html
@@ -4415,7 +4415,7 @@
 <h1>hardtanh<a class="headerlink" href="#hardtanh" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.hardtanh">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">hardtanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L593"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.hardtanh" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">hardtanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L593"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.hardtanh" title="Permalink to this definition">#</a></dt>
 <dd><p>This is the quantized version of <a class="reference internal" href="torch.nn.functional.hardtanh.html#torch.nn.functional.hardtanh" title="torch.nn.functional.hardtanh"><code class="xref py py-func docutils literal notranslate"><span class="pre">hardtanh()</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.interpolate.html b/2.9/generated/torch.ao.nn.quantized.functional.interpolate.html
index 5ffde7ca4f5..ed82f5da296 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.interpolate.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.interpolate.html
@@ -4415,7 +4415,7 @@
 <h1>interpolate<a class="headerlink" href="#interpolate" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.interpolate">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">interpolate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L394"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.interpolate" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">interpolate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L394"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.interpolate" title="Permalink to this definition">#</a></dt>
 <dd><p>Down/up samples the input to either the given <code class="xref py py-attr docutils literal notranslate"><span class="pre">size</span></code> or the given
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale_factor</span></code></p>
 <p>See <a class="reference internal" href="torch.nn.functional.interpolate.html#torch.nn.functional.interpolate" title="torch.nn.functional.interpolate"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.interpolate()</span></code></a> for implementation details.</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.leaky_relu.html b/2.9/generated/torch.ao.nn.quantized.functional.leaky_relu.html
index 0fbcdff10ac..5a394e60a5b 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.leaky_relu.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.leaky_relu.html
@@ -4415,7 +4415,7 @@
 <h1>leaky_relu<a class="headerlink" href="#leaky-relu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.leaky_relu">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">leaky_relu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.leaky_relu" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">leaky_relu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.leaky_relu" title="Permalink to this definition">#</a></dt>
 <dd><p>Quantized version of the.
 leaky_relu(input, negative_slope=0.01, inplace=False, scale, zero_point) -&gt; Tensor</p>
 <p>Applies element-wise,
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.linear.html b/2.9/generated/torch.ao.nn.quantized.functional.linear.html
index a44dea1c38a..f7b2951efdb 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.linear.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.linear.html
@@ -4415,7 +4415,7 @@
 <h1>linear<a class="headerlink" href="#linear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.linear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L439"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.linear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L439"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.linear" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a linear transformation to the incoming quantized data:
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mi>x</mi><msup><mi>A</mi><mi>T</mi></msup><mo>+</mo><mi>b</mi></mrow><annotation encoding="application/x-tex">y = xA^T + b</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.9247em;vertical-align:-0.0833em;"></span><span class="mord mathnormal">x</span><span class="mord"><span class="mord mathnormal">A</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8413em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight" style="margin-right:0.13889em;">T</span></span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal">b</span></span></span></span></span>.
 See <a class="reference internal" href="torch.ao.nn.quantized.Linear.html#torch.ao.nn.quantized.Linear" title="torch.ao.nn.quantized.Linear"><code class="xref py py-class docutils literal notranslate"><span class="pre">Linear</span></code></a></p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.max_pool1d.html b/2.9/generated/torch.ao.nn.quantized.functional.max_pool1d.html
index fff22808eb7..cbc36e9c15e 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.max_pool1d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.max_pool1d.html
@@ -4415,7 +4415,7 @@
 <h1>max_pool1d<a class="headerlink" href="#max-pool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.max_pool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L478"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.max_pool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L478"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.max_pool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D max pooling over a quantized input signal composed of
 several quantized input planes.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.max_pool2d.html b/2.9/generated/torch.ao.nn.quantized.functional.max_pool2d.html
index bfc5dbb6c48..e61e6a79972 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.max_pool2d.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.max_pool2d.html
@@ -4415,7 +4415,7 @@
 <h1>max_pool2d<a class="headerlink" href="#max-pool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.max_pool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L509"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.max_pool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L509"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.max_pool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D max pooling over a quantized input signal composed of
 several quantized input planes.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.threshold.html b/2.9/generated/torch.ao.nn.quantized.functional.threshold.html
index 2e26b810c8c..ffc3696470d 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.threshold.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.threshold.html
@@ -4415,7 +4415,7 @@
 <h1>threshold<a class="headerlink" href="#threshold" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.threshold">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">threshold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.threshold" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">threshold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.threshold" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the quantized version of the threshold function element-wise:</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mi>x</mi><mo>=</mo><mrow><mo fence="true">{</mo><mtable rowspacing="0.36em" columnalign="left left" columnspacing="1em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mi>x</mi></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mtext>if </mtext><mi>x</mi><mo>&gt;</mo><mtext>threshold</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mtext>value</mtext></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mtext>otherwise</mtext></mstyle></mtd></mtr></mtable></mrow></mrow><annotation encoding="application/x-tex">x = \begin{cases}
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.upsample.html b/2.9/generated/torch.ao.nn.quantized.functional.upsample.html
index 04a8c1f0305..5744fced74f 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.upsample.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.upsample.html
@@ -4415,7 +4415,7 @@
 <h1>upsample<a class="headerlink" href="#upsample" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.upsample">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">upsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L676"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.upsample" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">upsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L676"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.upsample" title="Permalink to this definition">#</a></dt>
 <dd><p>Upsamples the input to either the given <code class="xref py py-attr docutils literal notranslate"><span class="pre">size</span></code> or the given
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale_factor</span></code></p>
 <div class="admonition warning">
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.upsample_bilinear.html b/2.9/generated/torch.ao.nn.quantized.functional.upsample_bilinear.html
index d7486114a87..76a668baf29 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.upsample_bilinear.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.upsample_bilinear.html
@@ -4415,7 +4415,7 @@
 <h1>upsample_bilinear<a class="headerlink" href="#upsample-bilinear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.upsample_bilinear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">upsample_bilinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.upsample_bilinear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">upsample_bilinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.upsample_bilinear" title="Permalink to this definition">#</a></dt>
 <dd><p>Upsamples the input, using bilinear upsampling.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.ao.nn.quantized.functional.upsample_nearest.html b/2.9/generated/torch.ao.nn.quantized.functional.upsample_nearest.html
index 2fb3106e4fa..6332cb07a82 100644
--- a/2.9/generated/torch.ao.nn.quantized.functional.upsample_nearest.html
+++ b/2.9/generated/torch.ao.nn.quantized.functional.upsample_nearest.html
@@ -4415,7 +4415,7 @@
 <h1>upsample_nearest<a class="headerlink" href="#upsample-nearest" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.nn.quantized.functional.upsample_nearest">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">upsample_nearest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/nn/quantized/functional.py#L757"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.upsample_nearest" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.nn.quantized.functional.</span></span><span class="sig-name descname"><span class="pre">upsample_nearest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/nn/quantized/functional.py#L757"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.nn.quantized.functional.upsample_nearest" title="Permalink to this definition">#</a></dt>
 <dd><p>Upsamples the input, using nearest neighbours’ pixel values.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.ao.quantization.DeQuantStub.html b/2.9/generated/torch.ao.quantization.DeQuantStub.html
index b4d80ba5caa..0e322a298d7 100644
--- a/2.9/generated/torch.ao.quantization.DeQuantStub.html
+++ b/2.9/generated/torch.ao.quantization.DeQuantStub.html
@@ -4415,7 +4415,7 @@
 <h1>DeQuantStub<a class="headerlink" href="#dequantstub" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.DeQuantStub">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">DeQuantStub</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/stubs.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.DeQuantStub" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">DeQuantStub</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/stubs.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.DeQuantStub" title="Permalink to this definition">#</a></dt>
 <dd><p>Dequantize stub module, before calibration, this is same as identity,
 this will be swapped as <cite>nnq.DeQuantize</cite> in <cite>convert</cite>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.QuantStub.html b/2.9/generated/torch.ao.quantization.QuantStub.html
index a6cd40cc6d1..fbb89377c7b 100644
--- a/2.9/generated/torch.ao.quantization.QuantStub.html
+++ b/2.9/generated/torch.ao.quantization.QuantStub.html
@@ -4415,7 +4415,7 @@
 <h1>QuantStub<a class="headerlink" href="#quantstub" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.QuantStub">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">QuantStub</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/stubs.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.QuantStub" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">QuantStub</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/stubs.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.QuantStub" title="Permalink to this definition">#</a></dt>
 <dd><p>Quantize stub module, before calibration, this is same as an observer,
 it will be swapped as <cite>nnq.Quantize</cite> in <cite>convert</cite>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.QuantWrapper.html b/2.9/generated/torch.ao.quantization.QuantWrapper.html
index 835d5a58018..e168a3cfe2f 100644
--- a/2.9/generated/torch.ao.quantization.QuantWrapper.html
+++ b/2.9/generated/torch.ao.quantization.QuantWrapper.html
@@ -4415,7 +4415,7 @@
 <h1>QuantWrapper<a class="headerlink" href="#quantwrapper" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.QuantWrapper">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">QuantWrapper</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/stubs.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.QuantWrapper" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">QuantWrapper</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/stubs.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.QuantWrapper" title="Permalink to this definition">#</a></dt>
 <dd><p>A wrapper class that wraps the input module, adds QuantStub and
 DeQuantStub and surround the call to module with call to quant and dequant
 modules.</p>
diff --git a/2.9/generated/torch.ao.quantization.add_quant_dequant.html b/2.9/generated/torch.ao.quantization.add_quant_dequant.html
index 923e55020f1..edc8a2b72de 100644
--- a/2.9/generated/torch.ao.quantization.add_quant_dequant.html
+++ b/2.9/generated/torch.ao.quantization.add_quant_dequant.html
@@ -4415,7 +4415,7 @@
 <h1>add_quant_dequant<a class="headerlink" href="#add-quant-dequant" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.add_quant_dequant">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">add_quant_dequant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.add_quant_dequant" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">add_quant_dequant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.add_quant_dequant" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrap the leaf child module in QuantWrapper if it has a valid qconfig
 Note that this function will modify the children of module inplace and it
 can return a new module which wraps the input module as well.</p>
diff --git a/2.9/generated/torch.ao.quantization.backend_config.BackendConfig.html b/2.9/generated/torch.ao.quantization.backend_config.BackendConfig.html
index 7138d4945ba..36448226195 100644
--- a/2.9/generated/torch.ao.quantization.backend_config.BackendConfig.html
+++ b/2.9/generated/torch.ao.quantization.backend_config.BackendConfig.html
@@ -4415,7 +4415,7 @@
 <h1>BackendConfig<a class="headerlink" href="#backendconfig" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">BackendConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L289"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">BackendConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L289"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig" title="Permalink to this definition">#</a></dt>
 <dd><p>Config that defines the set of patterns that can be quantized on a given backend, and how reference
 quantized models can be produced from these patterns.</p>
 <p>A pattern in this context refers to a module, a functional, an operator, or a directed acyclic graph
@@ -4468,7 +4468,7 @@ <h1>BackendConfig<a class="headerlink" href="#backendconfig" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendConfig.from_dict">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L404"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.from_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L404"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.from_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="docutils literal notranslate"><span class="pre">BackendConfig</span></code> from a dictionary with the following items:</p>
 <blockquote>
 <div><p>“name”: the name of the target backend</p>
@@ -4483,7 +4483,7 @@ <h1>BackendConfig<a class="headerlink" href="#backendconfig" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendConfig.set_backend_pattern_config">
-<span class="sig-name descname"><span class="pre">set_backend_pattern_config</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">config</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.set_backend_pattern_config" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_backend_pattern_config</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">config</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.set_backend_pattern_config" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the config for an pattern that can be run on the target backend.
 This overrides any existing config for the given pattern.</p>
 <dl class="field-list simple">
@@ -4495,7 +4495,7 @@ <h1>BackendConfig<a class="headerlink" href="#backendconfig" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendConfig.set_backend_pattern_configs">
-<span class="sig-name descname"><span class="pre">set_backend_pattern_configs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">configs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L386"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.set_backend_pattern_configs" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_backend_pattern_configs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">configs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L386"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.set_backend_pattern_configs" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the configs for patterns that can be run on the target backend.
 This overrides any existing config for a given pattern if it was previously registered already.</p>
 <dl class="field-list simple">
@@ -4507,7 +4507,7 @@ <h1>BackendConfig<a class="headerlink" href="#backendconfig" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendConfig.set_name">
-<span class="sig-name descname"><span class="pre">set_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L367"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.set_name" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L367"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.set_name" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the name of the target backend.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4518,7 +4518,7 @@ <h1>BackendConfig<a class="headerlink" href="#backendconfig" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendConfig.to_dict">
-<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.to_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendConfig.to_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert this <code class="docutils literal notranslate"><span class="pre">BackendConfig</span></code> to a dictionary with the items described in
 <a class="reference internal" href="#torch.ao.quantization.backend_config.BackendConfig.from_dict" title="torch.ao.quantization.backend_config.BackendConfig.from_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_dict()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.backend_config.BackendPatternConfig.html b/2.9/generated/torch.ao.quantization.backend_config.BackendPatternConfig.html
index 9093c83abeb..05897d937dd 100644
--- a/2.9/generated/torch.ao.quantization.backend_config.BackendPatternConfig.html
+++ b/2.9/generated/torch.ao.quantization.backend_config.BackendPatternConfig.html
@@ -4415,14 +4415,14 @@
 <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">BackendPatternConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pattern</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">BackendPatternConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pattern</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig" title="Permalink to this definition">#</a></dt>
 <dd><p>Config object that specifies quantization behavior for a given operator pattern.
 For a detailed example usage, see <a class="reference internal" href="torch.ao.quantization.backend_config.BackendConfig.html#torch.ao.quantization.backend_config.BackendConfig" title="torch.ao.quantization.backend_config.BackendConfig"><code class="xref py py-class docutils literal notranslate"><span class="pre">BackendConfig</span></code></a>.</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.add_dtype_config">
-<span class="sig-name descname"><span class="pre">add_dtype_config</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype_config</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L512"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.add_dtype_config" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_dtype_config</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype_config</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L512"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.add_dtype_config" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a set of supported data types passed as arguments to quantize ops in the
 reference model spec.</p>
 <dl class="field-list simple">
@@ -4434,7 +4434,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.from_dict">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend_pattern_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L630"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.from_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend_pattern_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L630"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.from_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="docutils literal notranslate"><span class="pre">BackendPatternConfig</span></code> from a dictionary with the following items:</p>
 <blockquote>
 <div><p>“pattern”: the pattern being configured
@@ -4458,7 +4458,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.set_dtype_configs">
-<span class="sig-name descname"><span class="pre">set_dtype_configs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype_configs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_dtype_configs" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_dtype_configs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype_configs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_dtype_configs" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the supported data types passed as arguments to quantize ops in the
 reference model spec, overriding all previously registered data types.</p>
 <dl class="field-list simple">
@@ -4470,7 +4470,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.set_fused_module">
-<span class="sig-name descname"><span class="pre">set_fused_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fused_module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L567"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_fused_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_fused_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fused_module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L567"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_fused_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module that represents the fused implementation for this pattern.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4481,7 +4481,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.set_fuser_method">
-<span class="sig-name descname"><span class="pre">set_fuser_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fuser_method</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L576"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_fuser_method" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_fuser_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fuser_method</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L576"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_fuser_method" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the function that specifies how to fuse this BackendPatternConfig’s pattern.</p>
 <p>The first argument of this function should be <cite>is_qat</cite>, and the rest of the arguments
 should be the items in the tuple pattern. The return value of this function should be
@@ -4503,7 +4503,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.set_observation_type">
-<span class="sig-name descname"><span class="pre">set_observation_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observation_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L486"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_observation_type" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_observation_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observation_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L486"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_observation_type" title="Permalink to this definition">#</a></dt>
 <dd><p>Set how observers should be inserted in the graph for this pattern.</p>
 <p>Observation type here refers to how observers (or quant-dequant ops) will be placed
 in the graph. This is used to produce the desired reference patterns understood by
@@ -4528,7 +4528,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.set_pattern">
-<span class="sig-name descname"><span class="pre">set_pattern</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pattern</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L471"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_pattern" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_pattern</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pattern</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L471"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_pattern" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the pattern to configure.</p>
 <p>The pattern can be a float module, functional operator, pytorch operator, or a tuple
 combination of the above. Tuple patterns are treated as sequential patterns, and
@@ -4542,7 +4542,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.set_qat_module">
-<span class="sig-name descname"><span class="pre">set_qat_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qat_module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L548"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_qat_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_qat_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qat_module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L548"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_qat_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module that represents the QAT implementation for this pattern.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4553,7 +4553,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.set_reference_quantized_module">
-<span class="sig-name descname"><span class="pre">set_reference_quantized_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reference_quantized_module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L555"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_reference_quantized_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_reference_quantized_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reference_quantized_module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L555"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_reference_quantized_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module that represents the reference quantized implementation for
 this pattern’s root module.</p>
 <p>For more detail, see <a class="reference internal" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_root_module" title="torch.ao.quantization.backend_config.BackendPatternConfig.set_root_module"><code class="xref py py-func docutils literal notranslate"><span class="pre">set_root_module()</span></code></a>.</p>
@@ -4566,7 +4566,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.set_root_module">
-<span class="sig-name descname"><span class="pre">set_root_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root_module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L530"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_root_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_root_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root_module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L530"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.set_root_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module that represents the root for this pattern.</p>
 <p>When we construct the reference quantized model during the convert phase,
 the root modules (e.g. torch.nn.Linear for torch.ao.nn.intrinsic.LinearReLU)
@@ -4585,7 +4585,7 @@ <h1>BackendPatternConfig<a class="headerlink" href="#backendpatternconfig" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.BackendPatternConfig.to_dict">
-<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L706"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.to_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L706"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.BackendPatternConfig.to_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert this <code class="docutils literal notranslate"><span class="pre">BackendPatternConfig</span></code> to a dictionary with the items described in
 <a class="reference internal" href="#torch.ao.quantization.backend_config.BackendPatternConfig.from_dict" title="torch.ao.quantization.backend_config.BackendPatternConfig.from_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_dict()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.backend_config.DTypeConfig.html b/2.9/generated/torch.ao.quantization.backend_config.DTypeConfig.html
index 10f6e2a142b..102559c6328 100644
--- a/2.9/generated/torch.ao.quantization.backend_config.DTypeConfig.html
+++ b/2.9/generated/torch.ao.quantization.backend_config.DTypeConfig.html
@@ -4415,7 +4415,7 @@
 <h1>DTypeConfig<a class="headerlink" href="#dtypeconfig" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.DTypeConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">DTypeConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.DTypeConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">DTypeConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.DTypeConfig" title="Permalink to this definition">#</a></dt>
 <dd><p>Config object that specifies the supported data types passed as arguments to
 quantize ops in the reference model spec, for input and output activations,
 weights, and biases.</p>
@@ -4481,7 +4481,7 @@ <h1>DTypeConfig<a class="headerlink" href="#dtypeconfig" title="Permalink to thi
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.DTypeConfig.from_dict">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L231"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.DTypeConfig.from_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L231"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.DTypeConfig.from_dict" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Create a <code class="docutils literal notranslate"><span class="pre">DTypeConfig</span></code> from a dictionary with the following items (all optional):</dt><dd><p>“input_dtype”: torch.dtype or <code class="docutils literal notranslate"><span class="pre">DTypeWithConstraints</span></code>
 “output_dtype”: torch.dtype or <code class="docutils literal notranslate"><span class="pre">DTypeWithConstraints</span></code>
@@ -4499,7 +4499,7 @@ <h1>DTypeConfig<a class="headerlink" href="#dtypeconfig" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.DTypeConfig.to_dict">
-<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L266"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.DTypeConfig.to_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L266"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.DTypeConfig.to_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert this <code class="docutils literal notranslate"><span class="pre">DTypeConfig</span></code> to a dictionary with the items described in
 <a class="reference internal" href="#torch.ao.quantization.backend_config.DTypeConfig.from_dict" title="torch.ao.quantization.backend_config.DTypeConfig.from_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_dict()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.backend_config.DTypeWithConstraints.html b/2.9/generated/torch.ao.quantization.backend_config.DTypeWithConstraints.html
index c52cce2c77f..e8970c962ef 100644
--- a/2.9/generated/torch.ao.quantization.backend_config.DTypeWithConstraints.html
+++ b/2.9/generated/torch.ao.quantization.backend_config.DTypeWithConstraints.html
@@ -4415,7 +4415,7 @@
 <h1>DTypeWithConstraints<a class="headerlink" href="#dtypewithconstraints" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.DTypeWithConstraints">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">DTypeWithConstraints</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min_lower_bound</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max_upper_bound</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_min_lower_bound</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_max_upper_bound</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_exact_match</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point_exact_match</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.DTypeWithConstraints" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">DTypeWithConstraints</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min_lower_bound</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max_upper_bound</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_min_lower_bound</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_max_upper_bound</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_exact_match</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point_exact_match</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.DTypeWithConstraints" title="Permalink to this definition">#</a></dt>
 <dd><p>Config for specifying additional constraints for a given dtype, such as quantization
 value ranges, scale value ranges, and fixed quantization params, to be used in
 <a class="reference internal" href="torch.ao.quantization.backend_config.DTypeConfig.html#torch.ao.quantization.backend_config.DTypeConfig" title="torch.ao.quantization.backend_config.DTypeConfig"><code class="xref py py-class docutils literal notranslate"><span class="pre">DTypeConfig</span></code></a>.</p>
diff --git a/2.9/generated/torch.ao.quantization.backend_config.ObservationType.html b/2.9/generated/torch.ao.quantization.backend_config.ObservationType.html
index c0e688e640b..8a260e07e88 100644
--- a/2.9/generated/torch.ao.quantization.backend_config.ObservationType.html
+++ b/2.9/generated/torch.ao.quantization.backend_config.ObservationType.html
@@ -4415,7 +4415,7 @@
 <h1>ObservationType<a class="headerlink" href="#observationtype" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.backend_config.ObservationType">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">ObservationType</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/backend_config/backend_config.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.ObservationType" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.backend_config.</span></span><span class="sig-name descname"><span class="pre">ObservationType</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/backend_config/backend_config.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.backend_config.ObservationType" title="Permalink to this definition">#</a></dt>
 <dd><p>An enum that represents different ways of how an operator/operator pattern
 should be observed</p>
 <dl class="py attribute">
diff --git a/2.9/generated/torch.ao.quantization.compare_results.html b/2.9/generated/torch.ao.quantization.compare_results.html
index 8ae966646cf..87e927d54b1 100644
--- a/2.9/generated/torch.ao.quantization.compare_results.html
+++ b/2.9/generated/torch.ao.quantization.compare_results.html
@@ -4415,7 +4415,7 @@
 <h1>compare_results<a class="headerlink" href="#compare-results" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.compare_results">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">compare_results</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ref_results</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">actual_results</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/pt2e/_numeric_debugger.py#L297"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.compare_results" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">compare_results</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ref_results</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">actual_results</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/pt2e/_numeric_debugger.py#L297"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.compare_results" title="Permalink to this definition">#</a></dt>
 <dd><p>Given two dict mapping from <cite>debug_handle_id</cite> (int) to list of tensors
 return a map from <cite>debug_handle_id</cite> to <cite>NodeAccuracySummary</cite> that contains
 comparison information like SQNR, MSE etc.</p>
diff --git a/2.9/generated/torch.ao.quantization.convert.html b/2.9/generated/torch.ao.quantization.convert.html
index 14edc0f0013..cfa45da5760 100644
--- a/2.9/generated/torch.ao.quantization.convert.html
+++ b/2.9/generated/torch.ao.quantization.convert.html
@@ -4415,7 +4415,7 @@
 <h1>convert<a class="headerlink" href="#convert" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.convert">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">convert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_reference</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">convert_custom_config_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L624"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.convert" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">convert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_reference</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">convert_custom_config_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L624"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.convert" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts submodules in input module to a different module according to <cite>mapping</cite>
 by calling <cite>from_float</cite> method on the target module class. And remove qconfig at the
 end if remove_qconfig is set to True.</p>
diff --git a/2.9/generated/torch.ao.quantization.default_eval_fn.html b/2.9/generated/torch.ao.quantization.default_eval_fn.html
index 495e2f72092..7cb40c28d8d 100644
--- a/2.9/generated/torch.ao.quantization.default_eval_fn.html
+++ b/2.9/generated/torch.ao.quantization.default_eval_fn.html
@@ -4415,7 +4415,7 @@
 <h1>default_eval_fn<a class="headerlink" href="#default-eval-fn" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.default_eval_fn">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">default_eval_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">calib_data</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/__init__.py#L197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.default_eval_fn" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">default_eval_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">calib_data</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/__init__.py#L197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.default_eval_fn" title="Permalink to this definition">#</a></dt>
 <dd><p>Define the default evaluation function.</p>
 <p>Default evaluation function takes a torch.utils.data.Dataset or a list of
 input Tensors and run the model on the dataset</p>
diff --git a/2.9/generated/torch.ao.quantization.extract_results_from_loggers.html b/2.9/generated/torch.ao.quantization.extract_results_from_loggers.html
index 01cbb6701d8..b895415a49b 100644
--- a/2.9/generated/torch.ao.quantization.extract_results_from_loggers.html
+++ b/2.9/generated/torch.ao.quantization.extract_results_from_loggers.html
@@ -4415,7 +4415,7 @@
 <h1>extract_results_from_loggers<a class="headerlink" href="#extract-results-from-loggers" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.extract_results_from_loggers">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">extract_results_from_loggers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/pt2e/_numeric_debugger.py#L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.extract_results_from_loggers" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">extract_results_from_loggers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/pt2e/_numeric_debugger.py#L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.extract_results_from_loggers" title="Permalink to this definition">#</a></dt>
 <dd><p>For a given model, extract the tensors stats and related information for each debug handle.
 The reason we have a list of object, instead of Tensor is because the output of node may not be
 a Tensor, it could be (nested) list, tuple or dict as well.</p>
diff --git a/2.9/generated/torch.ao.quantization.fake_quantize.FakeQuantize.html b/2.9/generated/torch.ao.quantization.fake_quantize.FakeQuantize.html
index ae8e51ac304..1876c00a082 100644
--- a/2.9/generated/torch.ao.quantization.fake_quantize.FakeQuantize.html
+++ b/2.9/generated/torch.ao.quantization.fake_quantize.FakeQuantize.html
@@ -4415,7 +4415,7 @@
 <h1>FakeQuantize<a class="headerlink" href="#fakequantize" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.FakeQuantize">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">FakeQuantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observer=&lt;class</span> <span class="pre">'torch.ao.quantization.observer.MovingAverageMinMaxObserver'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">**observer_kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FakeQuantize" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">FakeQuantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observer=&lt;class</span> <span class="pre">'torch.ao.quantization.observer.MovingAverageMinMaxObserver'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">**observer_kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FakeQuantize" title="Permalink to this definition">#</a></dt>
 <dd><p>Simulate the quantize and dequantize operations in training time.</p>
 <p>The output of this module is given by:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">x_out</span> <span class="o">=</span> <span class="p">(</span>
diff --git a/2.9/generated/torch.ao.quantization.fake_quantize.FakeQuantizeBase.html b/2.9/generated/torch.ao.quantization.fake_quantize.FakeQuantizeBase.html
index 7f0758f8e11..de6eee20481 100644
--- a/2.9/generated/torch.ao.quantization.fake_quantize.FakeQuantizeBase.html
+++ b/2.9/generated/torch.ao.quantization.fake_quantize.FakeQuantizeBase.html
@@ -4415,7 +4415,7 @@
 <h1>FakeQuantizeBase<a class="headerlink" href="#fakequantizebase" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.FakeQuantizeBase">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">FakeQuantizeBase</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FakeQuantizeBase" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">FakeQuantizeBase</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L72"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FakeQuantizeBase" title="Permalink to this definition">#</a></dt>
 <dd><p>Base fake quantize module.</p>
 <p>Base fake quantize module
 Any fake quantize implementation should derive from this class.</p>
diff --git a/2.9/generated/torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize.html b/2.9/generated/torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize.html
index 60cee5f73ce..8353b6a4d7c 100644
--- a/2.9/generated/torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize.html
+++ b/2.9/generated/torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize.html
@@ -4415,14 +4415,14 @@
 <h1>FixedQParamsFakeQuantize<a class="headerlink" href="#fixedqparamsfakequantize" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">FixedQParamsFakeQuantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">FixedQParamsFakeQuantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize" title="Permalink to this definition">#</a></dt>
 <dd><p>Simulate quantize and dequantize in training time.</p>
 <p>Simulate quantize and dequantize with fixed quantization
 parameters in training time. Only per tensor quantization
 is supported.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L348"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L348"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FixedQParamsFakeQuantize.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a string representation of the object’s attributes.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize.html b/2.9/generated/torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize.html
index bf2981c2dfe..44ec6815742 100644
--- a/2.9/generated/torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize.html
+++ b/2.9/generated/torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize.html
@@ -4415,7 +4415,7 @@
 <h1>FusedMovingAvgObsFakeQuantize<a class="headerlink" href="#fusedmovingavgobsfakequantize" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">FusedMovingAvgObsFakeQuantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observer=&lt;class</span> <span class="pre">'torch.ao.quantization.observer.MovingAverageMinMaxObserver'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min=0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max=255</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">**observer_kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L359"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">FusedMovingAvgObsFakeQuantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observer=&lt;class</span> <span class="pre">'torch.ao.quantization.observer.MovingAverageMinMaxObserver'&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min=0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max=255</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">**observer_kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L359"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.FusedMovingAvgObsFakeQuantize" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a fused module to observe the tensor.</p>
 <p>Fused module that is used to observe the input tensor (compute min/max), compute
 scale/zero_point and fake_quantize the tensor.
diff --git a/2.9/generated/torch.ao.quantization.fake_quantize.disable_fake_quant.html b/2.9/generated/torch.ao.quantization.fake_quantize.disable_fake_quant.html
index 69c3a04dd79..997c9c62e6c 100644
--- a/2.9/generated/torch.ao.quantization.fake_quantize.disable_fake_quant.html
+++ b/2.9/generated/torch.ao.quantization.fake_quantize.disable_fake_quant.html
@@ -4415,7 +4415,7 @@
 <h1>disable_fake_quant<a class="headerlink" href="#disable-fake-quant" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.disable_fake_quant">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">disable_fake_quant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.disable_fake_quant" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">disable_fake_quant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.disable_fake_quant" title="Permalink to this definition">#</a></dt>
 <dd><p>Disable fake quantization for the module.</p>
 <p>Disable fake quantization for this module, if applicable. Example usage:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># model is any PyTorch model</span>
diff --git a/2.9/generated/torch.ao.quantization.fake_quantize.disable_observer.html b/2.9/generated/torch.ao.quantization.fake_quantize.disable_observer.html
index a7e8c4b16f7..cacdd037ca4 100644
--- a/2.9/generated/torch.ao.quantization.fake_quantize.disable_observer.html
+++ b/2.9/generated/torch.ao.quantization.fake_quantize.disable_observer.html
@@ -4415,7 +4415,7 @@
 <h1>disable_observer<a class="headerlink" href="#disable-observer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.disable_observer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">disable_observer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.disable_observer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">disable_observer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.disable_observer" title="Permalink to this definition">#</a></dt>
 <dd><p>Disable observation for this module.</p>
 <p>Disable observation for this module, if applicable. Example usage:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># model is any PyTorch model</span>
diff --git a/2.9/generated/torch.ao.quantization.fake_quantize.enable_fake_quant.html b/2.9/generated/torch.ao.quantization.fake_quantize.enable_fake_quant.html
index 12bb7b1f2af..5da7b9b1a60 100644
--- a/2.9/generated/torch.ao.quantization.fake_quantize.enable_fake_quant.html
+++ b/2.9/generated/torch.ao.quantization.fake_quantize.enable_fake_quant.html
@@ -4415,7 +4415,7 @@
 <h1>enable_fake_quant<a class="headerlink" href="#enable-fake-quant" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.enable_fake_quant">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">enable_fake_quant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L614"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.enable_fake_quant" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">enable_fake_quant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L614"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.enable_fake_quant" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable fake quantization for the module.</p>
 <p>Enable fake quantization for this module, if applicable. Example usage:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># model is any PyTorch model</span>
diff --git a/2.9/generated/torch.ao.quantization.fake_quantize.enable_observer.html b/2.9/generated/torch.ao.quantization.fake_quantize.enable_observer.html
index e130f416a9b..0fd1991747e 100644
--- a/2.9/generated/torch.ao.quantization.fake_quantize.enable_observer.html
+++ b/2.9/generated/torch.ao.quantization.fake_quantize.enable_observer.html
@@ -4415,7 +4415,7 @@
 <h1>enable_observer<a class="headerlink" href="#enable-observer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fake_quantize.enable_observer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">enable_observer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fake_quantize.py#L640"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.enable_observer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fake_quantize.</span></span><span class="sig-name descname"><span class="pre">enable_observer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fake_quantize.py#L640"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fake_quantize.enable_observer" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable observation for this module.</p>
 <p>Enable observation for this module, if applicable. Example usage:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="c1"># model is any PyTorch model</span>
diff --git a/2.9/generated/torch.ao.quantization.fuse_modules.fuse_modules.html b/2.9/generated/torch.ao.quantization.fuse_modules.fuse_modules.html
index 78f137f3f34..9f4c0fe467d 100644
--- a/2.9/generated/torch.ao.quantization.fuse_modules.fuse_modules.html
+++ b/2.9/generated/torch.ao.quantization.fuse_modules.fuse_modules.html
@@ -4415,7 +4415,7 @@
 <h1>fuse_modules<a class="headerlink" href="#fuse-modules" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fuse_modules.fuse_modules">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fuse_modules.</span></span><span class="sig-name descname"><span class="pre">fuse_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">modules_to_fuse</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fuser_func=&lt;function</span> <span class="pre">fuse_known_modules&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fuse_custom_config_dict=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fuse_modules.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fuse_modules.fuse_modules" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fuse_modules.</span></span><span class="sig-name descname"><span class="pre">fuse_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">modules_to_fuse</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fuser_func=&lt;function</span> <span class="pre">fuse_known_modules&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fuse_custom_config_dict=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fuse_modules.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fuse_modules.fuse_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse a list of modules into a single module.</p>
 <p>Fuses only the following sequence of modules:
 conv, bn
diff --git a/2.9/generated/torch.ao.quantization.fx.custom_config.ConvertCustomConfig.html b/2.9/generated/torch.ao.quantization.fx.custom_config.ConvertCustomConfig.html
index 9b595e5cbe6..3483156e29f 100644
--- a/2.9/generated/torch.ao.quantization.fx.custom_config.ConvertCustomConfig.html
+++ b/2.9/generated/torch.ao.quantization.fx.custom_config.ConvertCustomConfig.html
@@ -4415,7 +4415,7 @@
 <h1>ConvertCustomConfig<a class="headerlink" href="#convertcustomconfig" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.ConvertCustomConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fx.custom_config.</span></span><span class="sig-name descname"><span class="pre">ConvertCustomConfig</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fx.custom_config.</span></span><span class="sig-name descname"><span class="pre">ConvertCustomConfig</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig" title="Permalink to this definition">#</a></dt>
 <dd><p>Custom configuration for <a class="reference internal" href="torch.ao.quantization.quantize_fx.convert_fx.html#torch.ao.quantization.quantize_fx.convert_fx" title="torch.ao.quantization.quantize_fx.convert_fx"><code class="xref py py-func docutils literal notranslate"><span class="pre">convert_fx()</span></code></a>.</p>
 <p>Example usage:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">convert_custom_config</span> <span class="o">=</span> <span class="n">ConvertCustomConfig</span><span class="p">()</span>             <span class="o">.</span><span class="n">set_observed_to_quantized_mapping</span><span class="p">(</span><span class="n">ObservedCustomModule</span><span class="p">,</span> <span class="n">QuantizedCustomModule</span><span class="p">)</span>             <span class="o">.</span><span class="n">set_preserved_attributes</span><span class="p">([</span><span class="s2">&quot;attr1&quot;</span><span class="p">,</span> <span class="s2">&quot;attr2&quot;</span><span class="p">])</span>
@@ -4425,7 +4425,7 @@ <h1>ConvertCustomConfig<a class="headerlink" href="#convertcustomconfig" title="
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.ConvertCustomConfig.from_dict">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">convert_custom_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.from_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">convert_custom_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.from_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="docutils literal notranslate"><span class="pre">ConvertCustomConfig</span></code> from a dictionary with the following items:</p>
 <blockquote>
 <div><p>“observed_to_quantized_custom_module_class”: a nested dictionary mapping from quantization
@@ -4447,7 +4447,7 @@ <h1>ConvertCustomConfig<a class="headerlink" href="#convertcustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.ConvertCustomConfig.set_observed_to_quantized_mapping">
-<span class="sig-name descname"><span class="pre">set_observed_to_quantized_mapping</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observed_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quantized_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">QuantType.STATIC</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L393"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.set_observed_to_quantized_mapping" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_observed_to_quantized_mapping</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observed_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quantized_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">QuantType.STATIC</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L393"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.set_observed_to_quantized_mapping" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the mapping from a custom observed module class to a custom quantized module class.</p>
 <p>The quantized module class must have a <code class="docutils literal notranslate"><span class="pre">from_observed</span></code> class method that converts the observed module class
 to the quantized module class.</p>
@@ -4460,7 +4460,7 @@ <h1>ConvertCustomConfig<a class="headerlink" href="#convertcustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.ConvertCustomConfig.set_preserved_attributes">
-<span class="sig-name descname"><span class="pre">set_preserved_attributes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attributes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.set_preserved_attributes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_preserved_attributes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attributes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.set_preserved_attributes" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the names of the attributes that will persist in the graph module even if they are not used in
 the model’s <code class="docutils literal notranslate"><span class="pre">forward</span></code> method.</p>
 <dl class="field-list simple">
@@ -4472,7 +4472,7 @@ <h1>ConvertCustomConfig<a class="headerlink" href="#convertcustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.ConvertCustomConfig.to_dict">
-<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L451"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.to_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L451"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.to_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert this <code class="docutils literal notranslate"><span class="pre">ConvertCustomConfig</span></code> to a dictionary with the items described in
 <a class="reference internal" href="#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.from_dict" title="torch.ao.quantization.fx.custom_config.ConvertCustomConfig.from_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_dict()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.fx.custom_config.FuseCustomConfig.html b/2.9/generated/torch.ao.quantization.fx.custom_config.FuseCustomConfig.html
index e7ea0954cbc..63e67170c96 100644
--- a/2.9/generated/torch.ao.quantization.fx.custom_config.FuseCustomConfig.html
+++ b/2.9/generated/torch.ao.quantization.fx.custom_config.FuseCustomConfig.html
@@ -4415,7 +4415,7 @@
 <h1>FuseCustomConfig<a class="headerlink" href="#fusecustomconfig" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.FuseCustomConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fx.custom_config.</span></span><span class="sig-name descname"><span class="pre">FuseCustomConfig</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L471"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.FuseCustomConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fx.custom_config.</span></span><span class="sig-name descname"><span class="pre">FuseCustomConfig</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L471"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.FuseCustomConfig" title="Permalink to this definition">#</a></dt>
 <dd><p>Custom configuration for <a class="reference internal" href="torch.ao.quantization.quantize_fx.fuse_fx.html#torch.ao.quantization.quantize_fx.fuse_fx" title="torch.ao.quantization.quantize_fx.fuse_fx"><code class="xref py py-func docutils literal notranslate"><span class="pre">fuse_fx()</span></code></a>.</p>
 <p>Example usage:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">fuse_custom_config</span> <span class="o">=</span> <span class="n">FuseCustomConfig</span><span class="p">()</span><span class="o">.</span><span class="n">set_preserved_attributes</span><span class="p">(</span>
@@ -4427,7 +4427,7 @@ <h1>FuseCustomConfig<a class="headerlink" href="#fusecustomconfig" title="Permal
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.FuseCustomConfig.from_dict">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fuse_custom_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.FuseCustomConfig.from_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fuse_custom_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.FuseCustomConfig.from_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="docutils literal notranslate"><span class="pre">ConvertCustomConfig</span></code> from a dictionary with the following items:</p>
 <blockquote>
 <div><p>“preserved_attributes”: a list of attributes that persist even if they are not used in <code class="docutils literal notranslate"><span class="pre">forward</span></code></p>
@@ -4442,7 +4442,7 @@ <h1>FuseCustomConfig<a class="headerlink" href="#fusecustomconfig" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.FuseCustomConfig.set_preserved_attributes">
-<span class="sig-name descname"><span class="pre">set_preserved_attributes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attributes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L489"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.FuseCustomConfig.set_preserved_attributes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_preserved_attributes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attributes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L489"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.FuseCustomConfig.set_preserved_attributes" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the names of the attributes that will persist in the graph module even if they are not used in
 the model’s <code class="docutils literal notranslate"><span class="pre">forward</span></code> method.</p>
 <dl class="field-list simple">
@@ -4454,7 +4454,7 @@ <h1>FuseCustomConfig<a class="headerlink" href="#fusecustomconfig" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.FuseCustomConfig.to_dict">
-<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L513"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.FuseCustomConfig.to_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L513"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.FuseCustomConfig.to_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert this <code class="docutils literal notranslate"><span class="pre">FuseCustomConfig</span></code> to a dictionary with the items described in
 <a class="reference internal" href="torch.ao.quantization.fx.custom_config.ConvertCustomConfig.html#torch.ao.quantization.fx.custom_config.ConvertCustomConfig.from_dict" title="torch.ao.quantization.fx.custom_config.ConvertCustomConfig.from_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_dict()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.fx.custom_config.PrepareCustomConfig.html b/2.9/generated/torch.ao.quantization.fx.custom_config.PrepareCustomConfig.html
index 6a63a79ffc0..197a41a81ad 100644
--- a/2.9/generated/torch.ao.quantization.fx.custom_config.PrepareCustomConfig.html
+++ b/2.9/generated/torch.ao.quantization.fx.custom_config.PrepareCustomConfig.html
@@ -4415,7 +4415,7 @@
 <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fx.custom_config.</span></span><span class="sig-name descname"><span class="pre">PrepareCustomConfig</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fx.custom_config.</span></span><span class="sig-name descname"><span class="pre">PrepareCustomConfig</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig" title="Permalink to this definition">#</a></dt>
 <dd><p>Custom configuration for <a class="reference internal" href="torch.ao.quantization.quantize_fx.prepare_fx.html#torch.ao.quantization.quantize_fx.prepare_fx" title="torch.ao.quantization.quantize_fx.prepare_fx"><code class="xref py py-func docutils literal notranslate"><span class="pre">prepare_fx()</span></code></a> and
 <a class="reference internal" href="torch.ao.quantization.quantize_fx.prepare_qat_fx.html#torch.ao.quantization.quantize_fx.prepare_qat_fx" title="torch.ao.quantization.quantize_fx.prepare_qat_fx"><code class="xref py py-func docutils literal notranslate"><span class="pre">prepare_qat_fx()</span></code></a>.</p>
 <p>Example usage:</p>
@@ -4426,7 +4426,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.from_dict">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prepare_custom_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.from_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prepare_custom_config_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.from_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="docutils literal notranslate"><span class="pre">PrepareCustomConfig</span></code> from a dictionary with the following items:</p>
 <blockquote>
 <div><p>“standalone_module_name”: a list of (module_name, qconfig_mapping, example_inputs,
@@ -4452,7 +4452,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_float_to_observed_mapping">
-<span class="sig-name descname"><span class="pre">set_float_to_observed_mapping</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">float_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">observed_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">QuantType.STATIC</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_float_to_observed_mapping" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_float_to_observed_mapping</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">float_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">observed_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">QuantType.STATIC</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_float_to_observed_mapping" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the mapping from a custom float module class to a custom observed module class.</p>
 <p>The observed module class must have a <code class="docutils literal notranslate"><span class="pre">from_float</span></code> class method that converts the float module class
 to the observed module class. This is currently only supported for static quantization.</p>
@@ -4465,7 +4465,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_input_quantized_indexes">
-<span class="sig-name descname"><span class="pre">set_input_quantized_indexes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indexes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_input_quantized_indexes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_input_quantized_indexes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indexes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_input_quantized_indexes" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the indexes of the inputs of the graph that should be quantized.
 Inputs are otherwise assumed to be in fp32 by default instead.</p>
 <dl class="field-list simple">
@@ -4477,7 +4477,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_non_traceable_module_classes">
-<span class="sig-name descname"><span class="pre">set_non_traceable_module_classes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_classes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L150"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_non_traceable_module_classes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_non_traceable_module_classes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_classes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L150"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_non_traceable_module_classes" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the modules that are not symbolically traceable, identified by class.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4488,7 +4488,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_non_traceable_module_names">
-<span class="sig-name descname"><span class="pre">set_non_traceable_module_names</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_names</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_non_traceable_module_names" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_non_traceable_module_names</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_names</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_non_traceable_module_names" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the modules that are not symbolically traceable, identified by name.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4499,7 +4499,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_output_quantized_indexes">
-<span class="sig-name descname"><span class="pre">set_output_quantized_indexes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indexes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_output_quantized_indexes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_output_quantized_indexes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indexes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_output_quantized_indexes" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the indexes of the outputs of the graph that should be quantized.
 Outputs are otherwise assumed to be in fp32 by default instead.</p>
 <dl class="field-list simple">
@@ -4511,7 +4511,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_preserved_attributes">
-<span class="sig-name descname"><span class="pre">set_preserved_attributes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attributes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_preserved_attributes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_preserved_attributes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attributes</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_preserved_attributes" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the names of the attributes that will persist in the graph module even if they are not used in
 the model’s <code class="docutils literal notranslate"><span class="pre">forward</span></code> method.</p>
 <dl class="field-list simple">
@@ -4523,7 +4523,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_standalone_module_class">
-<span class="sig-name descname"><span class="pre">set_standalone_module_class</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_standalone_module_class" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_standalone_module_class</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_standalone_module_class" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the configuration for running a standalone module identified by <code class="docutils literal notranslate"><span class="pre">module_class</span></code>.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">qconfig_mapping</span></code> is None, the parent <code class="docutils literal notranslate"><span class="pre">qconfig_mapping</span></code> will be used instead.
 If <code class="docutils literal notranslate"><span class="pre">prepare_custom_config</span></code> is None, an empty <code class="docutils literal notranslate"><span class="pre">PrepareCustomConfig</span></code> will be used.
@@ -4537,7 +4537,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_standalone_module_name">
-<span class="sig-name descname"><span class="pre">set_standalone_module_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_standalone_module_name" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_standalone_module_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.set_standalone_module_name" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the configuration for running a standalone module identified by <code class="docutils literal notranslate"><span class="pre">module_name</span></code>.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">qconfig_mapping</span></code> is None, the parent <code class="docutils literal notranslate"><span class="pre">qconfig_mapping</span></code> will be used instead.
 If <code class="docutils literal notranslate"><span class="pre">prepare_custom_config</span></code> is None, an empty <code class="docutils literal notranslate"><span class="pre">PrepareCustomConfig</span></code> will be used.
@@ -4551,7 +4551,7 @@ <h1>PrepareCustomConfig<a class="headerlink" href="#preparecustomconfig" title="
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.to_dict">
-<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.to_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.to_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert this <code class="docutils literal notranslate"><span class="pre">PrepareCustomConfig</span></code> to a dictionary with the items described in
 <a class="reference internal" href="#torch.ao.quantization.fx.custom_config.PrepareCustomConfig.from_dict" title="torch.ao.quantization.fx.custom_config.PrepareCustomConfig.from_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_dict()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.fx.custom_config.StandaloneModuleConfigEntry.html b/2.9/generated/torch.ao.quantization.fx.custom_config.StandaloneModuleConfigEntry.html
index b79c4497fe1..b20b7c08771 100644
--- a/2.9/generated/torch.ao.quantization.fx.custom_config.StandaloneModuleConfigEntry.html
+++ b/2.9/generated/torch.ao.quantization.fx.custom_config.StandaloneModuleConfigEntry.html
@@ -4415,7 +4415,7 @@
 <h1>StandaloneModuleConfigEntry<a class="headerlink" href="#standalonemoduleconfigentry" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.fx.custom_config.StandaloneModuleConfigEntry">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fx.custom_config.</span></span><span class="sig-name descname"><span class="pre">StandaloneModuleConfigEntry</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'Optional[QConfigMapping]'</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'tuple[Any,</span> <span class="pre">...]'</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'Optional[PrepareCustomConfig]'</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'Optional[BackendConfig]'</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/fx/custom_config.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.StandaloneModuleConfigEntry" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.fx.custom_config.</span></span><span class="sig-name descname"><span class="pre">StandaloneModuleConfigEntry</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'Optional[QConfigMapping]'</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'tuple[Any,</span> <span class="pre">...]'</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'Optional[PrepareCustomConfig]'</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'Optional[BackendConfig]'</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/fx/custom_config.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.fx.custom_config.StandaloneModuleConfigEntry" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.quantization.generate_numeric_debug_handle.html b/2.9/generated/torch.ao.quantization.generate_numeric_debug_handle.html
index 1fd8a03d2b1..9b06a022ccb 100644
--- a/2.9/generated/torch.ao.quantization.generate_numeric_debug_handle.html
+++ b/2.9/generated/torch.ao.quantization.generate_numeric_debug_handle.html
@@ -4415,7 +4415,7 @@
 <h1>generate_numeric_debug_handle<a class="headerlink" href="#generate-numeric-debug-handle" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.generate_numeric_debug_handle">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">generate_numeric_debug_handle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ep</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/pt2e/_numeric_debugger.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.generate_numeric_debug_handle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">generate_numeric_debug_handle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ep</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/pt2e/_numeric_debugger.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.generate_numeric_debug_handle" title="Permalink to this definition">#</a></dt>
 <dd><p>Attach numeric_debug_handle_id for all nodes in the graph module of the given
 ExportedProgram, like conv2d, squeeze, conv1d, etc, except for placeholder.
 Notice that nodes like getattr are out of scope since they are not in the graph.</p>
diff --git a/2.9/generated/torch.ao.quantization.observer.AffineQuantizedObserverBase.html b/2.9/generated/torch.ao.quantization.observer.AffineQuantizedObserverBase.html
index 85a6bf3cb2a..06986499271 100644
--- a/2.9/generated/torch.ao.quantization.observer.AffineQuantizedObserverBase.html
+++ b/2.9/generated/torch.ao.quantization.observer.AffineQuantizedObserverBase.html
@@ -4415,7 +4415,7 @@
 <h1>AffineQuantizedObserverBase<a class="headerlink" href="#affinequantizedobserverbase" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.AffineQuantizedObserverBase">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">AffineQuantizedObserverBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mapping_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">granularity</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserve_zero</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point_domain</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">ZeroPointDomain.INT</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1808"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">AffineQuantizedObserverBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mapping_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">granularity</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserve_zero</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_point_domain</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">ZeroPointDomain.INT</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1808"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase" title="Permalink to this definition">#</a></dt>
 <dd><p>Observer module for affine quantization (<a class="github reference external" href="https://github.com/pytorch/ao/tree/main/torchao/quantization#affine-quantization">pytorch/ao</a>)</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4429,7 +4429,7 @@ <h1>AffineQuantizedObserverBase<a class="headerlink" href="#affinequantizedobser
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.AffineQuantizedObserverBase.calculate_qparams">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">calculate_qparams</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1858"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase.calculate_qparams" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">calculate_qparams</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1858"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase.calculate_qparams" title="Permalink to this definition">#</a></dt>
 <dd><p>Calculate quantization parameter based on the stats attached to the observer module
 and returns a tuple of scale and zero_point Tensor</p>
 <dl class="field-list simple">
@@ -4441,7 +4441,7 @@ <h1>AffineQuantizedObserverBase<a class="headerlink" href="#affinequantizedobser
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.AffineQuantizedObserverBase.convert">
-<span class="sig-name descname"><span class="pre">convert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">observer_node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1864"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase.convert" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">convert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">observer_node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1864"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase.convert" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts the observer node in the graph into its quantized representation</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4455,7 +4455,7 @@ <h1>AffineQuantizedObserverBase<a class="headerlink" href="#affinequantizedobser
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.AffineQuantizedObserverBase.forward">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1852"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase.forward" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1852"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>forward function should take the input tensor
 and updates internal stats and return the original input Tensor</p>
 <dl class="field-list simple">
@@ -4467,7 +4467,7 @@ <h1>AffineQuantizedObserverBase<a class="headerlink" href="#affinequantizedobser
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.AffineQuantizedObserverBase.with_args">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">with_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase.with_args" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">with_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.AffineQuantizedObserverBase.with_args" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper that allows creation of class factories.</p>
 <p>This can be useful when there is a need to create classes with the same
 constructor arguments, but different instances. Can be used in conjunction with
diff --git a/2.9/generated/torch.ao.quantization.observer.Granularity.html b/2.9/generated/torch.ao.quantization.observer.Granularity.html
index e3cb4159c9b..404a308807c 100644
--- a/2.9/generated/torch.ao.quantization.observer.Granularity.html
+++ b/2.9/generated/torch.ao.quantization.observer.Granularity.html
@@ -4415,7 +4415,7 @@
 <h1>Granularity<a class="headerlink" href="#granularity" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.Granularity">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">Granularity</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.Granularity" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">Granularity</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.Granularity" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class for representing the granularity of quantization.</p>
 <p>This class serves as a parent for specific granularity types used in
 quantization operations, such as per-tensor or per-axis quantization.</p>
diff --git a/2.9/generated/torch.ao.quantization.observer.HistogramObserver.html b/2.9/generated/torch.ao.quantization.observer.HistogramObserver.html
index cfa57373ce5..f6be41d177b 100644
--- a/2.9/generated/torch.ao.quantization.observer.HistogramObserver.html
+++ b/2.9/generated/torch.ao.quantization.observer.HistogramObserver.html
@@ -4415,7 +4415,7 @@
 <h1>HistogramObserver<a class="headerlink" href="#histogramobserver" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.HistogramObserver">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">HistogramObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">bins</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_tensor_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factory_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L980"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.HistogramObserver" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">HistogramObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">bins</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_tensor_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factory_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L980"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.HistogramObserver" title="Permalink to this definition">#</a></dt>
 <dd><p>The module records the running histogram of tensor values along with
 min/max values. <code class="docutils literal notranslate"><span class="pre">calculate_qparams</span></code> will calculate scale and zero_point.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.observer.MappingType.html b/2.9/generated/torch.ao.quantization.observer.MappingType.html
index 711817672ca..c4ed9ca23f2 100644
--- a/2.9/generated/torch.ao.quantization.observer.MappingType.html
+++ b/2.9/generated/torch.ao.quantization.observer.MappingType.html
@@ -4415,7 +4415,7 @@
 <h1>MappingType<a class="headerlink" href="#mappingtype" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.MappingType">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">MappingType</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1622"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MappingType" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">MappingType</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1622"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MappingType" title="Permalink to this definition">#</a></dt>
 <dd><p>How floating point number is mapped to integer number</p>
 <p>symmetric mapping means floating point range is symmetrically mapped to integer range
 let’s say we have floating point range (-3.5, 10.2) and integer range (-8, 7) (int4)
diff --git a/2.9/generated/torch.ao.quantization.observer.MinMaxObserver.html b/2.9/generated/torch.ao.quantization.observer.MinMaxObserver.html
index 9fffb0d95c0..7af28ddcb25 100644
--- a/2.9/generated/torch.ao.quantization.observer.MinMaxObserver.html
+++ b/2.9/generated/torch.ao.quantization.observer.MinMaxObserver.html
@@ -4415,7 +4415,7 @@
 <h1>MinMaxObserver<a class="headerlink" href="#minmaxobserver" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.MinMaxObserver">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">MinMaxObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_tensor_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factory_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L435"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MinMaxObserver" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">MinMaxObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_tensor_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factory_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L435"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MinMaxObserver" title="Permalink to this definition">#</a></dt>
 <dd><p>Observer module for computing the quantization parameters based on the
 running min and max values.</p>
 <p>This observer uses the tensor min/max statistics to compute the quantization
@@ -4475,19 +4475,19 @@ <h1>MinMaxObserver<a class="headerlink" href="#minmaxobserver" title="Permalink
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.MinMaxObserver.calculate_qparams">
-<span class="sig-name descname"><span class="pre">calculate_qparams</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MinMaxObserver.calculate_qparams" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">calculate_qparams</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MinMaxObserver.calculate_qparams" title="Permalink to this definition">#</a></dt>
 <dd><p>Calculates the quantization parameters.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.MinMaxObserver.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x_orig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L553"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MinMaxObserver.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x_orig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L553"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MinMaxObserver.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Records the running minimum and maximum of <code class="docutils literal notranslate"><span class="pre">x</span></code>.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.MinMaxObserver.reset_min_max_vals">
-<span class="sig-name descname"><span class="pre">reset_min_max_vals</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MinMaxObserver.reset_min_max_vals" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_min_max_vals</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MinMaxObserver.reset_min_max_vals" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets the min/max values.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.ao.quantization.observer.MovingAverageMinMaxObserver.html b/2.9/generated/torch.ao.quantization.observer.MovingAverageMinMaxObserver.html
index 5d1862b4b37..9df5cea1da6 100644
--- a/2.9/generated/torch.ao.quantization.observer.MovingAverageMinMaxObserver.html
+++ b/2.9/generated/torch.ao.quantization.observer.MovingAverageMinMaxObserver.html
@@ -4415,7 +4415,7 @@
 <h1>MovingAverageMinMaxObserver<a class="headerlink" href="#movingaverageminmaxobserver" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.MovingAverageMinMaxObserver">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">MovingAverageMinMaxObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">averaging_constant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_tensor_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L582"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MovingAverageMinMaxObserver" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">MovingAverageMinMaxObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">averaging_constant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_tensor_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L582"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MovingAverageMinMaxObserver" title="Permalink to this definition">#</a></dt>
 <dd><p>Observer module for computing the quantization parameters based on the
 moving average of the min and max values.</p>
 <p>This observer computes the quantization parameters based on the moving
diff --git a/2.9/generated/torch.ao.quantization.observer.MovingAveragePerChannelMinMaxObserver.html b/2.9/generated/torch.ao.quantization.observer.MovingAveragePerChannelMinMaxObserver.html
index 6fa5da11bd0..1fa24f23afc 100644
--- a/2.9/generated/torch.ao.quantization.observer.MovingAveragePerChannelMinMaxObserver.html
+++ b/2.9/generated/torch.ao.quantization.observer.MovingAveragePerChannelMinMaxObserver.html
@@ -4415,7 +4415,7 @@
 <h1>MovingAveragePerChannelMinMaxObserver<a class="headerlink" href="#movingaverageperchannelminmaxobserver" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.MovingAveragePerChannelMinMaxObserver">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">MovingAveragePerChannelMinMaxObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">averaging_constant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ch_axis</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_channel_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L890"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MovingAveragePerChannelMinMaxObserver" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">MovingAveragePerChannelMinMaxObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">averaging_constant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ch_axis</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_channel_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L890"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.MovingAveragePerChannelMinMaxObserver" title="Permalink to this definition">#</a></dt>
 <dd><p>Observer module for computing the quantization parameters based on the
 running per channel min and max values.</p>
 <p>This observer uses the tensor min/max statistics to compute the per channel
diff --git a/2.9/generated/torch.ao.quantization.observer.NoopObserver.html b/2.9/generated/torch.ao.quantization.observer.NoopObserver.html
index e5d9e8ad14b..64fa2798f28 100644
--- a/2.9/generated/torch.ao.quantization.observer.NoopObserver.html
+++ b/2.9/generated/torch.ao.quantization.observer.NoopObserver.html
@@ -4415,7 +4415,7 @@
 <h1>NoopObserver<a class="headerlink" href="#noopobserver" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.NoopObserver">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">NoopObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.float16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_op_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.NoopObserver" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">NoopObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.float16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_op_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.NoopObserver" title="Permalink to this definition">#</a></dt>
 <dd><p>Observer that doesn’t do anything and just passes its configuration to the
 quantized module’s <code class="docutils literal notranslate"><span class="pre">.from_float()</span></code>.</p>
 <p>Primarily used for quantization to float16 which doesn’t require determining
diff --git a/2.9/generated/torch.ao.quantization.observer.ObserverBase.html b/2.9/generated/torch.ao.quantization.observer.ObserverBase.html
index 4c462befb21..ebb0b70630a 100644
--- a/2.9/generated/torch.ao.quantization.observer.ObserverBase.html
+++ b/2.9/generated/torch.ao.quantization.observer.ObserverBase.html
@@ -4415,7 +4415,7 @@
 <h1>ObserverBase<a class="headerlink" href="#observerbase" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.ObserverBase">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">ObserverBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L150"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.ObserverBase" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">ObserverBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L150"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.ObserverBase" title="Permalink to this definition">#</a></dt>
 <dd><p>Base observer Module.
 Any observer implementation should derive from this class.</p>
 <p>Concrete observers should follow the same API. In forward, they will update
@@ -4434,7 +4434,7 @@ <h1>ObserverBase<a class="headerlink" href="#observerbase" title="Permalink to t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.ObserverBase.with_args">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">with_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.ObserverBase.with_args" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">with_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.ObserverBase.with_args" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper that allows creation of class factories.</p>
 <p>This can be useful when there is a need to create classes with the same
 constructor arguments, but different instances. Can be used in conjunction with
@@ -4452,7 +4452,7 @@ <h1>ObserverBase<a class="headerlink" href="#observerbase" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.ObserverBase.with_callable_args">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">with_callable_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L123"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.ObserverBase.with_callable_args" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">with_callable_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L123"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.ObserverBase.with_callable_args" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper that allows creation of class factories args that need to be
 called at construction time.</p>
 <p>This can be useful when there is a need to create classes with the same
diff --git a/2.9/generated/torch.ao.quantization.observer.PerAxis.html b/2.9/generated/torch.ao.quantization.observer.PerAxis.html
index 7bf22d18e2e..bbcd5609a05 100644
--- a/2.9/generated/torch.ao.quantization.observer.PerAxis.html
+++ b/2.9/generated/torch.ao.quantization.observer.PerAxis.html
@@ -4415,7 +4415,7 @@
 <h1>PerAxis<a class="headerlink" href="#peraxis" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PerAxis">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerAxis</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">axis</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1710"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerAxis" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerAxis</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">axis</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1710"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerAxis" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents per-axis granularity in quantization.</p>
 <p>This granularity type calculates different quantization parameters
 along a specified axis of the tensor.</p>
diff --git a/2.9/generated/torch.ao.quantization.observer.PerBlock.html b/2.9/generated/torch.ao.quantization.observer.PerBlock.html
index cadc125f957..12c75fabbfc 100644
--- a/2.9/generated/torch.ao.quantization.observer.PerBlock.html
+++ b/2.9/generated/torch.ao.quantization.observer.PerBlock.html
@@ -4415,7 +4415,7 @@
 <h1>PerBlock<a class="headerlink" href="#perblock" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PerBlock">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerBlock</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">block_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1685"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerBlock" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerBlock</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">block_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1685"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerBlock" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents per-block granularity in quantization. See
 <code class="xref py py-func docutils literal notranslate"><span class="pre">quantize_affine()</span></code> for docs for
 <cite>block_size</cite></p>
diff --git a/2.9/generated/torch.ao.quantization.observer.PerChannelMinMaxObserver.html b/2.9/generated/torch.ao.quantization.observer.PerChannelMinMaxObserver.html
index cdc5b178902..7f84431af03 100644
--- a/2.9/generated/torch.ao.quantization.observer.PerChannelMinMaxObserver.html
+++ b/2.9/generated/torch.ao.quantization.observer.PerChannelMinMaxObserver.html
@@ -4415,7 +4415,7 @@
 <h1>PerChannelMinMaxObserver<a class="headerlink" href="#perchannelminmaxobserver" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PerChannelMinMaxObserver">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerChannelMinMaxObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ch_axis</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_channel_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factory_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L681"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerChannelMinMaxObserver" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerChannelMinMaxObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ch_axis</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.per_channel_affine</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce_range</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factory_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.1920928955078125e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L681"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerChannelMinMaxObserver" title="Permalink to this definition">#</a></dt>
 <dd><p>Observer module for computing the quantization parameters based on the
 running per channel min and max values.</p>
 <p>This observer uses the tensor min/max statistics to compute the per channel
@@ -4447,7 +4447,7 @@ <h1>PerChannelMinMaxObserver<a class="headerlink" href="#perchannelminmaxobserve
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PerChannelMinMaxObserver.reset_min_max_vals">
-<span class="sig-name descname"><span class="pre">reset_min_max_vals</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L876"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerChannelMinMaxObserver.reset_min_max_vals" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_min_max_vals</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L876"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerChannelMinMaxObserver.reset_min_max_vals" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets the min/max values.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.ao.quantization.observer.PerGroup.html b/2.9/generated/torch.ao.quantization.observer.PerGroup.html
index 89a14d48034..024c445bbaa 100644
--- a/2.9/generated/torch.ao.quantization.observer.PerGroup.html
+++ b/2.9/generated/torch.ao.quantization.observer.PerGroup.html
@@ -4415,7 +4415,7 @@
 <h1>PerGroup<a class="headerlink" href="#pergroup" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PerGroup">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerGroup</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1729"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerGroup" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerGroup</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1729"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerGroup" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents per-channel group granularity in quantization.</p>
 <p>This granularity type calculates different quantization parameters
 for each group of &lt;group_size&gt; elements.</p>
diff --git a/2.9/generated/torch.ao.quantization.observer.PerRow.html b/2.9/generated/torch.ao.quantization.observer.PerRow.html
index e960d098e12..674f8da3b2f 100644
--- a/2.9/generated/torch.ao.quantization.observer.PerRow.html
+++ b/2.9/generated/torch.ao.quantization.observer.PerRow.html
@@ -4415,7 +4415,7 @@
 <h1>PerRow<a class="headerlink" href="#perrow" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PerRow">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerRow</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1750"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerRow" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerRow</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1750"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerRow" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents row-wise granularity in quantization.</p>
 <p>This is a special case of per-axis quantization and is unique to Float8 matmuls
 where the input is quantized with a block_size of (1, …, input.shape[-1]). And the weight
diff --git a/2.9/generated/torch.ao.quantization.observer.PerTensor.html b/2.9/generated/torch.ao.quantization.observer.PerTensor.html
index a5b8ec8d60d..f66b061b7ce 100644
--- a/2.9/generated/torch.ao.quantization.observer.PerTensor.html
+++ b/2.9/generated/torch.ao.quantization.observer.PerTensor.html
@@ -4415,7 +4415,7 @@
 <h1>PerTensor<a class="headerlink" href="#pertensor" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PerTensor">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerTensor</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1699"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerTensor" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerTensor</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1699"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerTensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents per-tensor granularity in quantization.</p>
 <p>This granularity type calculates the quantization parameters
 based off the entire tensor.</p>
diff --git a/2.9/generated/torch.ao.quantization.observer.PerToken.html b/2.9/generated/torch.ao.quantization.observer.PerToken.html
index 646ad671467..61d94f642f4 100644
--- a/2.9/generated/torch.ao.quantization.observer.PerToken.html
+++ b/2.9/generated/torch.ao.quantization.observer.PerToken.html
@@ -4415,7 +4415,7 @@
 <h1>PerToken<a class="headerlink" href="#pertoken" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PerToken">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerToken</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1760"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerToken" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PerToken</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1760"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PerToken" title="Permalink to this definition">#</a></dt>
 <dd><p>Represents per-token granularity in quantization.</p>
 <p>This granularity type calculates a different set of quantization parameters
 for each token, which is represented as the last dimension of the tensor.</p>
diff --git a/2.9/generated/torch.ao.quantization.observer.PlaceholderObserver.html b/2.9/generated/torch.ao.quantization.observer.PlaceholderObserver.html
index 8f0ae566303..0331ced399b 100644
--- a/2.9/generated/torch.ao.quantization.observer.PlaceholderObserver.html
+++ b/2.9/generated/torch.ao.quantization.observer.PlaceholderObserver.html
@@ -4415,7 +4415,7 @@
 <h1>PlaceholderObserver<a class="headerlink" href="#placeholderobserver" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.PlaceholderObserver">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PlaceholderObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.float32</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_op_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1455"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PlaceholderObserver" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">PlaceholderObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.float32</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_op_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quant_max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qscheme</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dynamic</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1455"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.PlaceholderObserver" title="Permalink to this definition">#</a></dt>
 <dd><p>Observer that doesn’t do anything and just passes its configuration to the
 quantized module’s <code class="docutils literal notranslate"><span class="pre">.from_float()</span></code>.</p>
 <p>Can be used for quantization to float16 which doesn’t require determining
diff --git a/2.9/generated/torch.ao.quantization.observer.RecordingObserver.html b/2.9/generated/torch.ao.quantization.observer.RecordingObserver.html
index 10a6051e123..9e47aaa53c4 100644
--- a/2.9/generated/torch.ao.quantization.observer.RecordingObserver.html
+++ b/2.9/generated/torch.ao.quantization.observer.RecordingObserver.html
@@ -4415,7 +4415,7 @@
 <h1>RecordingObserver<a class="headerlink" href="#recordingobserver" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.RecordingObserver">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">RecordingObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1526"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.RecordingObserver" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">RecordingObserver</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.quint8</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1526"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.RecordingObserver" title="Permalink to this definition">#</a></dt>
 <dd><p>The module is mainly for debug and records the tensor values during runtime.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.observer.TorchAODType.html b/2.9/generated/torch.ao.quantization.observer.TorchAODType.html
index 6381b23a206..78458e85981 100644
--- a/2.9/generated/torch.ao.quantization.observer.TorchAODType.html
+++ b/2.9/generated/torch.ao.quantization.observer.TorchAODType.html
@@ -4415,7 +4415,7 @@
 <h1>TorchAODType<a class="headerlink" href="#torchaodtype" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.TorchAODType">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">TorchAODType</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1659"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.TorchAODType" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">TorchAODType</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1659"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.TorchAODType" title="Permalink to this definition">#</a></dt>
 <dd><p>Placeholder for dtypes that do not exist in PyTorch core yet.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.ao.quantization.observer.ZeroPointDomain.html b/2.9/generated/torch.ao.quantization.observer.ZeroPointDomain.html
index 8b2e5e5424a..36f1d9c6e74 100644
--- a/2.9/generated/torch.ao.quantization.observer.ZeroPointDomain.html
+++ b/2.9/generated/torch.ao.quantization.observer.ZeroPointDomain.html
@@ -4415,7 +4415,7 @@
 <h1>ZeroPointDomain<a class="headerlink" href="#zeropointdomain" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.ZeroPointDomain">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">ZeroPointDomain</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1646"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.ZeroPointDomain" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">ZeroPointDomain</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1646"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.ZeroPointDomain" title="Permalink to this definition">#</a></dt>
 <dd><p>Enum that indicate whether zero_point is in integer domain or floating point domain</p>
 <p>integer domain: quantized_val = (float_val / scale) (integer) + zero_point (integer)
 float domain: quantized_val = (float_val - (zero_point (float) - scale * mid_point)) / scale
diff --git a/2.9/generated/torch.ao.quantization.observer.default_debug_observer.html b/2.9/generated/torch.ao.quantization.observer.default_debug_observer.html
index a512de9f769..087941b3aa7 100644
--- a/2.9/generated/torch.ao.quantization.observer.default_debug_observer.html
+++ b/2.9/generated/torch.ao.quantization.observer.default_debug_observer.html
@@ -4415,7 +4415,7 @@
 <h1>default_debug_observer<a class="headerlink" href="#default-debug-observer" title="Permalink to this heading">#</a></h1>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.default_debug_observer">
-<span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">default_debug_observer</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1526"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.default_debug_observer" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">default_debug_observer</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1526"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.default_debug_observer" title="Permalink to this definition">#</a></dt>
 <dd><p>Default debug-only observer.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.ao.quantization.observer.default_placeholder_observer.html b/2.9/generated/torch.ao.quantization.observer.default_placeholder_observer.html
index 86b7dc76cd3..b2492e3f689 100644
--- a/2.9/generated/torch.ao.quantization.observer.default_placeholder_observer.html
+++ b/2.9/generated/torch.ao.quantization.observer.default_placeholder_observer.html
@@ -4415,7 +4415,7 @@
 <h1>default_placeholder_observer<a class="headerlink" href="#default-placeholder-observer" title="Permalink to this heading">#</a></h1>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.default_placeholder_observer">
-<span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">default_placeholder_observer</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1455"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.default_placeholder_observer" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">default_placeholder_observer</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1455"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.default_placeholder_observer" title="Permalink to this definition">#</a></dt>
 <dd><p>Default placeholder observer, usually used for quantization to torch.float16.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.ao.quantization.observer.get_block_size.html b/2.9/generated/torch.ao.quantization.observer.get_block_size.html
index 2c150ae0b32..c75fd233eab 100644
--- a/2.9/generated/torch.ao.quantization.observer.get_block_size.html
+++ b/2.9/generated/torch.ao.quantization.observer.get_block_size.html
@@ -4415,7 +4415,7 @@
 <h1>get_block_size<a class="headerlink" href="#get-block-size" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.get_block_size">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">get_block_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">granularity</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.get_block_size" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">get_block_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">granularity</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.get_block_size" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the block size based on the input shape and granularity type.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.observer.get_observer_state_dict.html b/2.9/generated/torch.ao.quantization.observer.get_observer_state_dict.html
index 8c8042ecb2f..9a3467fa3a6 100644
--- a/2.9/generated/torch.ao.quantization.observer.get_observer_state_dict.html
+++ b/2.9/generated/torch.ao.quantization.observer.get_observer_state_dict.html
@@ -4415,7 +4415,7 @@
 <h1>get_observer_state_dict<a class="headerlink" href="#get-observer-state-dict" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.get_observer_state_dict">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">get_observer_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L1985"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.get_observer_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">get_observer_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L1985"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.get_observer_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the state dict corresponding to the observer stats.
 Traverse the model state_dict and extract out the stats.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.ao.quantization.observer.load_observer_state_dict.html b/2.9/generated/torch.ao.quantization.observer.load_observer_state_dict.html
index b6214f95f8d..71f67d2b776 100644
--- a/2.9/generated/torch.ao.quantization.observer.load_observer_state_dict.html
+++ b/2.9/generated/torch.ao.quantization.observer.load_observer_state_dict.html
@@ -4415,7 +4415,7 @@
 <h1>load_observer_state_dict<a class="headerlink" href="#load-observer-state-dict" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.observer.load_observer_state_dict">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">load_observer_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obs_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/observer.py#L2004"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.load_observer_state_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.observer.</span></span><span class="sig-name descname"><span class="pre">load_observer_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obs_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/observer.py#L2004"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.observer.load_observer_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Given input model and a state_dict containing model observer stats,
 load the stats back into the model. The observer state_dict can be saved
 using torch.ao.quantization.get_observer_state_dict</p>
diff --git a/2.9/generated/torch.ao.quantization.prepare.html b/2.9/generated/torch.ao.quantization.prepare.html
index dd1e37375e4..8c91d855e35 100644
--- a/2.9/generated/torch.ao.quantization.prepare.html
+++ b/2.9/generated/torch.ao.quantization.prepare.html
@@ -4415,7 +4415,7 @@
 <h1>prepare<a class="headerlink" href="#prepare" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.prepare">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">prepare</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">observer_non_leaf_module_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.prepare" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">prepare</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">observer_non_leaf_module_list</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.prepare" title="Permalink to this definition">#</a></dt>
 <dd><p>Prepares a copy of the model for quantization calibration or quantization-aware training.</p>
 <p>Quantization configuration should be assigned preemptively
 to individual submodules in <cite>.qconfig</cite> attribute.</p>
diff --git a/2.9/generated/torch.ao.quantization.prepare_for_propagation_comparison.html b/2.9/generated/torch.ao.quantization.prepare_for_propagation_comparison.html
index e6e19d6a794..8496fe757c0 100644
--- a/2.9/generated/torch.ao.quantization.prepare_for_propagation_comparison.html
+++ b/2.9/generated/torch.ao.quantization.prepare_for_propagation_comparison.html
@@ -4415,7 +4415,7 @@
 <h1>prepare_for_propagation_comparison<a class="headerlink" href="#prepare-for-propagation-comparison" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.prepare_for_propagation_comparison">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">prepare_for_propagation_comparison</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/pt2e/_numeric_debugger.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.prepare_for_propagation_comparison" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">prepare_for_propagation_comparison</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/pt2e/_numeric_debugger.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.prepare_for_propagation_comparison" title="Permalink to this definition">#</a></dt>
 <dd><p>Add output loggers to node that has numeric_debug_handle</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.prepare_qat.html b/2.9/generated/torch.ao.quantization.prepare_qat.html
index bac285a08b5..d19c0766b48 100644
--- a/2.9/generated/torch.ao.quantization.prepare_qat.html
+++ b/2.9/generated/torch.ao.quantization.prepare_qat.html
@@ -4415,7 +4415,7 @@
 <h1>prepare_qat<a class="headerlink" href="#prepare-qat" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.prepare_qat">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">prepare_qat</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.prepare_qat" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">prepare_qat</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.prepare_qat" title="Permalink to this definition">#</a></dt>
 <dd><p>Prepares a copy of the model for quantization calibration or
 quantization-aware training and converts it to quantized version.</p>
 <p>Quantization configuration should be assigned preemptively
diff --git a/2.9/generated/torch.ao.quantization.propagate_qconfig_.html b/2.9/generated/torch.ao.quantization.propagate_qconfig_.html
index 6a8dee08944..0977da186ea 100644
--- a/2.9/generated/torch.ao.quantization.propagate_qconfig_.html
+++ b/2.9/generated/torch.ao.quantization.propagate_qconfig_.html
@@ -4415,7 +4415,7 @@
 <h1><a class="reference internal" href="#propagate-qconfig">propagate_qconfig</a><a class="headerlink" href="#propagate-qconfig" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.propagate_qconfig_">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">propagate_qconfig_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.propagate_qconfig_" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">propagate_qconfig_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.propagate_qconfig_" title="Permalink to this definition">#</a></dt>
 <dd><p>Propagate qconfig through the module hierarchy and assign <cite>qconfig</cite>
 attribute on each leaf module</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.pt2e.export_utils.model_is_exported.html b/2.9/generated/torch.ao.quantization.pt2e.export_utils.model_is_exported.html
index 40a1bfcc9a2..a9ff1a76724 100644
--- a/2.9/generated/torch.ao.quantization.pt2e.export_utils.model_is_exported.html
+++ b/2.9/generated/torch.ao.quantization.pt2e.export_utils.model_is_exported.html
@@ -4415,7 +4415,7 @@
 <h1>model_is_exported<a class="headerlink" href="#model-is-exported" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.pt2e.export_utils.model_is_exported">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.pt2e.export_utils.</span></span><span class="sig-name descname"><span class="pre">model_is_exported</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/pt2e/export_utils.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.pt2e.export_utils.model_is_exported" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.pt2e.export_utils.</span></span><span class="sig-name descname"><span class="pre">model_is_exported</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/pt2e/export_utils.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.pt2e.export_utils.model_is_exported" title="Permalink to this definition">#</a></dt>
 <dd><p>Return True if the <cite>torch.nn.Module</cite> was exported, False otherwise
 (e.g. if the model was FX symbolically traced or not traced at all).</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.pt2e.lowering.lower_pt2e_quantized_to_x86.html b/2.9/generated/torch.ao.quantization.pt2e.lowering.lower_pt2e_quantized_to_x86.html
index 6cae8a96a8c..10e78c397f4 100644
--- a/2.9/generated/torch.ao.quantization.pt2e.lowering.lower_pt2e_quantized_to_x86.html
+++ b/2.9/generated/torch.ao.quantization.pt2e.lowering.lower_pt2e_quantized_to_x86.html
@@ -4415,7 +4415,7 @@
 <h1>lower_pt2e_quantized_to_x86<a class="headerlink" href="#lower-pt2e-quantized-to-x86" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.pt2e.lowering.lower_pt2e_quantized_to_x86">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.pt2e.lowering.</span></span><span class="sig-name descname"><span class="pre">lower_pt2e_quantized_to_x86</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/pt2e/lowering.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.pt2e.lowering.lower_pt2e_quantized_to_x86" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.pt2e.lowering.</span></span><span class="sig-name descname"><span class="pre">lower_pt2e_quantized_to_x86</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/pt2e/lowering.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.pt2e.lowering.lower_pt2e_quantized_to_x86" title="Permalink to this definition">#</a></dt>
 <dd><p>Lower a PT2E-qantized model to x86 backend.</p>
 <p>Args:
 * <cite>model</cite> (torch.fx.GraphModule): a model quantized by PT2E quantization flow.
diff --git a/2.9/generated/torch.ao.quantization.qconfig.QConfig.html b/2.9/generated/torch.ao.quantization.qconfig.QConfig.html
index 77979a367f3..2a23914ad3b 100644
--- a/2.9/generated/torch.ao.quantization.qconfig.QConfig.html
+++ b/2.9/generated/torch.ao.quantization.qconfig.QConfig.html
@@ -4415,7 +4415,7 @@
 <h1>QConfig<a class="headerlink" href="#qconfig" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig.QConfig">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.qconfig.</span></span><span class="sig-name descname"><span class="pre">QConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">activation</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig.QConfig" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.qconfig.</span></span><span class="sig-name descname"><span class="pre">QConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">activation</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig.QConfig" title="Permalink to this definition">#</a></dt>
 <dd><p>Describes how to quantize a layer or a part of the network by providing
 settings (observer classes) for activations and weights respectively.</p>
 <p>Note that QConfig needs to contain observer <strong>classes</strong> (like MinMaxObserver) or a callable that returns
diff --git a/2.9/generated/torch.ao.quantization.qconfig_mapping.QConfigMapping.html b/2.9/generated/torch.ao.quantization.qconfig_mapping.QConfigMapping.html
index 79b6c0e3638..7f2b14fa81a 100644
--- a/2.9/generated/torch.ao.quantization.qconfig_mapping.QConfigMapping.html
+++ b/2.9/generated/torch.ao.quantization.qconfig_mapping.QConfigMapping.html
@@ -4415,7 +4415,7 @@
 <h1>QConfigMapping<a class="headerlink" href="#qconfigmapping" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.QConfigMapping">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.qconfig_mapping.</span></span><span class="sig-name descname"><span class="pre">QConfigMapping</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.qconfig_mapping.</span></span><span class="sig-name descname"><span class="pre">QConfigMapping</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping" title="Permalink to this definition">#</a></dt>
 <dd><p>Mapping from model ops to <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.ao.quantization.QConfig</span></code> s.</p>
 <p>The user can specify QConfigs using the following methods (in increasing match priority):</p>
 <blockquote>
@@ -4442,7 +4442,7 @@ <h1>QConfigMapping<a class="headerlink" href="#qconfigmapping" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.QConfigMapping.from_dict">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qconfig_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L347"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.from_dict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qconfig_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L347"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.from_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <code class="docutils literal notranslate"><span class="pre">QConfigMapping</span></code> from a dictionary with the following keys (all optional):</p>
 <blockquote>
 <div><p>“” (for global QConfig)</p>
@@ -4461,7 +4461,7 @@ <h1>QConfigMapping<a class="headerlink" href="#qconfigmapping" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.QConfigMapping.set_global">
-<span class="sig-name descname"><span class="pre">set_global</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">global_qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_global" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_global</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">global_qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_global" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the global (default) QConfig.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4472,7 +4472,7 @@ <h1>QConfigMapping<a class="headerlink" href="#qconfigmapping" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name">
-<span class="sig-name descname"><span class="pre">set_module_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L284"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_module_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L284"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the QConfig for modules matching the given module name.
 If the QConfig for an existing module name was already set, the new QConfig will override the old one.</p>
 <dl class="field-list simple">
@@ -4484,7 +4484,7 @@ <h1>QConfigMapping<a class="headerlink" href="#qconfigmapping" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name_object_type_order">
-<span class="sig-name descname"><span class="pre">set_module_name_object_type_order</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">object_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L292"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name_object_type_order" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_module_name_object_type_order</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">object_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L292"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name_object_type_order" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the QConfig for modules matching a combination of the given module name, object type,
 and the index at which the module appears.</p>
 <p>If the QConfig for an existing (module name, object type, index)  was already set, the new QConfig
@@ -4498,7 +4498,7 @@ <h1>QConfigMapping<a class="headerlink" href="#qconfigmapping" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name_regex">
-<span class="sig-name descname"><span class="pre">set_module_name_regex</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name_regex</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name_regex" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_module_name_regex</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name_regex</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_module_name_regex" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the QConfig for modules matching the given regex string.</p>
 <p>Regexes will be matched in the order in which they are registered through this method.
 Thus, the caller should register more specific patterns first, e.g.:</p>
@@ -4521,7 +4521,7 @@ <h1>QConfigMapping<a class="headerlink" href="#qconfigmapping" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.QConfigMapping.set_object_type">
-<span class="sig-name descname"><span class="pre">set_object_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_object_type" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_object_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">object_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.set_object_type" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the QConfig for a given module type, function, or method name.
 If the QConfig for an existing object type was already set, the new QConfig will override the old one.</p>
 <dl class="field-list simple">
@@ -4533,7 +4533,7 @@ <h1>QConfigMapping<a class="headerlink" href="#qconfigmapping" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.QConfigMapping.to_dict">
-<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.to_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.QConfigMapping.to_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert this <code class="docutils literal notranslate"><span class="pre">QConfigMapping</span></code> to a dictionary with the following keys:</p>
 <blockquote>
 <div><p>“” (for global QConfig)</p>
diff --git a/2.9/generated/torch.ao.quantization.qconfig_mapping.get_default_qat_qconfig_mapping.html b/2.9/generated/torch.ao.quantization.qconfig_mapping.get_default_qat_qconfig_mapping.html
index de56976e736..c1f2614fba1 100644
--- a/2.9/generated/torch.ao.quantization.qconfig_mapping.get_default_qat_qconfig_mapping.html
+++ b/2.9/generated/torch.ao.quantization.qconfig_mapping.get_default_qat_qconfig_mapping.html
@@ -4415,7 +4415,7 @@
 <h1>get_default_qat_qconfig_mapping<a class="headerlink" href="#get-default-qat-qconfig-mapping" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.get_default_qat_qconfig_mapping">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.qconfig_mapping.</span></span><span class="sig-name descname"><span class="pre">get_default_qat_qconfig_mapping</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'x86'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.get_default_qat_qconfig_mapping" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.qconfig_mapping.</span></span><span class="sig-name descname"><span class="pre">get_default_qat_qconfig_mapping</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'x86'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.get_default_qat_qconfig_mapping" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the default QConfigMapping for quantization aware training.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.qconfig_mapping.get_default_qconfig_mapping.html b/2.9/generated/torch.ao.quantization.qconfig_mapping.get_default_qconfig_mapping.html
index d22481aa33f..6829a09eadf 100644
--- a/2.9/generated/torch.ao.quantization.qconfig_mapping.get_default_qconfig_mapping.html
+++ b/2.9/generated/torch.ao.quantization.qconfig_mapping.get_default_qconfig_mapping.html
@@ -4415,7 +4415,7 @@
 <h1>get_default_qconfig_mapping<a class="headerlink" href="#get-default-qconfig-mapping" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.qconfig_mapping.get_default_qconfig_mapping">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.qconfig_mapping.</span></span><span class="sig-name descname"><span class="pre">get_default_qconfig_mapping</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'x86'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/qconfig_mapping.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.get_default_qconfig_mapping" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.qconfig_mapping.</span></span><span class="sig-name descname"><span class="pre">get_default_qconfig_mapping</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'x86'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/qconfig_mapping.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.qconfig_mapping.get_default_qconfig_mapping" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the default QConfigMapping for post training quantization.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.quantize.html b/2.9/generated/torch.ao.quantization.quantize.html
index 254f4b3892e..bd8a63a416a 100644
--- a/2.9/generated/torch.ao.quantization.quantize.html
+++ b/2.9/generated/torch.ao.quantization.quantize.html
@@ -4415,7 +4415,7 @@
 <h1>quantize<a class="headerlink" href="#quantize" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.quantize">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">quantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L449"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">quantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L449"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize" title="Permalink to this definition">#</a></dt>
 <dd><p>Quantize the input float model with post training static quantization.</p>
 <p>First it will prepare the model for calibration, then it calls
 <cite>run_fn</cite> which will run the calibration step, after that we will
diff --git a/2.9/generated/torch.ao.quantization.quantize_dynamic.html b/2.9/generated/torch.ao.quantization.quantize_dynamic.html
index cf8357c37f7..f349fcc8be2 100644
--- a/2.9/generated/torch.ao.quantization.quantize_dynamic.html
+++ b/2.9/generated/torch.ao.quantization.quantize_dynamic.html
@@ -4415,7 +4415,7 @@
 <h1>quantize_dynamic<a class="headerlink" href="#quantize-dynamic" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.quantize_dynamic">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">quantize_dynamic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L479"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_dynamic" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">quantize_dynamic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.qint8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L479"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_dynamic" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts a float model to dynamic (i.e. weights-only) quantized model.</p>
 <p>Replaces specified modules with dynamic weight-only quantized versions and output the quantized model.</p>
 <p>For simplest usage provide <cite>dtype</cite> argument that can be float16 or qint8. Weight-only quantization
diff --git a/2.9/generated/torch.ao.quantization.quantize_fx.convert_fx.html b/2.9/generated/torch.ao.quantization.quantize_fx.convert_fx.html
index ca3bff0329a..054993c5d57 100644
--- a/2.9/generated/torch.ao.quantization.quantize_fx.convert_fx.html
+++ b/2.9/generated/torch.ao.quantization.quantize_fx.convert_fx.html
@@ -4415,7 +4415,7 @@
 <h1>convert_fx<a class="headerlink" href="#convert-fx" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.quantize_fx.convert_fx">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.quantize_fx.</span></span><span class="sig-name descname"><span class="pre">convert_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">convert_custom_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_remove_qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_original_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize_fx.py#L566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_fx.convert_fx" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.quantize_fx.</span></span><span class="sig-name descname"><span class="pre">convert_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graph_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">convert_custom_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_remove_qconfig</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_original_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize_fx.py#L566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_fx.convert_fx" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert a calibrated or trained model to a quantized model</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.quantize_fx.fuse_fx.html b/2.9/generated/torch.ao.quantization.quantize_fx.fuse_fx.html
index b8171ad8306..4b9947ac2b1 100644
--- a/2.9/generated/torch.ao.quantization.quantize_fx.fuse_fx.html
+++ b/2.9/generated/torch.ao.quantization.quantize_fx.fuse_fx.html
@@ -4415,7 +4415,7 @@
 <h1>fuse_fx<a class="headerlink" href="#fuse-fx" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.quantize_fx.fuse_fx">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.quantize_fx.</span></span><span class="sig-name descname"><span class="pre">fuse_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fuse_custom_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize_fx.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_fx.fuse_fx" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.quantize_fx.</span></span><span class="sig-name descname"><span class="pre">fuse_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fuse_custom_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize_fx.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_fx.fuse_fx" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse modules like conv+bn, conv+bn+relu etc, model must be in eval mode.
 Fusion rules are defined in torch.ao.quantization.fx.fusion_pattern.py</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.ao.quantization.quantize_fx.prepare_fx.html b/2.9/generated/torch.ao.quantization.quantize_fx.prepare_fx.html
index 99db879b5c8..bd3fab77c21 100644
--- a/2.9/generated/torch.ao.quantization.quantize_fx.prepare_fx.html
+++ b/2.9/generated/torch.ao.quantization.quantize_fx.prepare_fx.html
@@ -4415,7 +4415,7 @@
 <h1>prepare_fx<a class="headerlink" href="#prepare-fx" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.quantize_fx.prepare_fx">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.quantize_fx.</span></span><span class="sig-name descname"><span class="pre">prepare_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_equalization_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize_fx.py#L253"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_fx.prepare_fx" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.quantize_fx.</span></span><span class="sig-name descname"><span class="pre">prepare_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_equalization_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize_fx.py#L253"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_fx.prepare_fx" title="Permalink to this definition">#</a></dt>
 <dd><p>Prepare a model for post training quantization</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.quantize_fx.prepare_qat_fx.html b/2.9/generated/torch.ao.quantization.quantize_fx.prepare_qat_fx.html
index 3219b5d4af9..b37ddbcf7e3 100644
--- a/2.9/generated/torch.ao.quantization.quantize_fx.prepare_qat_fx.html
+++ b/2.9/generated/torch.ao.quantization.quantize_fx.prepare_qat_fx.html
@@ -4415,7 +4415,7 @@
 <h1>prepare_qat_fx<a class="headerlink" href="#prepare-qat-fx" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.quantize_fx.prepare_qat_fx">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.quantize_fx.</span></span><span class="sig-name descname"><span class="pre">prepare_qat_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize_fx.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_fx.prepare_qat_fx" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.quantize_fx.</span></span><span class="sig-name descname"><span class="pre">prepare_qat_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qconfig_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepare_custom_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize_fx.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_fx.prepare_qat_fx" title="Permalink to this definition">#</a></dt>
 <dd><p>Prepare a model for quantization aware training</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.quantize_qat.html b/2.9/generated/torch.ao.quantization.quantize_qat.html
index a6a83bd01eb..d570b9d460c 100644
--- a/2.9/generated/torch.ao.quantization.quantize_qat.html
+++ b/2.9/generated/torch.ao.quantization.quantize_qat.html
@@ -4415,7 +4415,7 @@
 <h1>quantize_qat<a class="headerlink" href="#quantize-qat" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.quantize_qat">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">quantize_qat</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L600"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_qat" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">quantize_qat</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L600"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.quantize_qat" title="Permalink to this definition">#</a></dt>
 <dd><p>Do quantization aware training and output a quantized model</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.ao.quantization.swap_module.html b/2.9/generated/torch.ao.quantization.swap_module.html
index 4aa07ce0588..0ac0de9e6c9 100644
--- a/2.9/generated/torch.ao.quantization.swap_module.html
+++ b/2.9/generated/torch.ao.quantization.swap_module.html
@@ -4415,7 +4415,7 @@
 <h1>swap_module<a class="headerlink" href="#swap-module" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ao.quantization.swap_module">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">swap_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_module_class_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/quantization/quantize.py#L739"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.swap_module" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.ao.quantization.</span></span><span class="sig-name descname"><span class="pre">swap_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_module_class_mapping</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_precomputed_fake_quant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/quantization/quantize.py#L739"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.quantization.swap_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Swaps the module if it has a quantized counterpart and it has an
 <cite>observer</cite> attached.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.are_deterministic_algorithms_enabled.html b/2.9/generated/torch.are_deterministic_algorithms_enabled.html
index 70e388c3295..95816885654 100644
--- a/2.9/generated/torch.are_deterministic_algorithms_enabled.html
+++ b/2.9/generated/torch.are_deterministic_algorithms_enabled.html
@@ -4404,7 +4404,7 @@
 <h1>torch.are_deterministic_algorithms_enabled<a class="headerlink" href="#torch-are-deterministic-algorithms-enabled" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.are_deterministic_algorithms_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">are_deterministic_algorithms_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.are_deterministic_algorithms_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">are_deterministic_algorithms_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.are_deterministic_algorithms_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if the global deterministic flag is turned on. Refer to
 <a class="reference internal" href="torch.use_deterministic_algorithms.html#torch.use_deterministic_algorithms" title="torch.use_deterministic_algorithms"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.use_deterministic_algorithms()</span></code></a> documentation for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.atleast_1d.html b/2.9/generated/torch.atleast_1d.html
index 836ccd8a492..99bdff25471 100644
--- a/2.9/generated/torch.atleast_1d.html
+++ b/2.9/generated/torch.atleast_1d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.atleast_1d<a class="headerlink" href="#torch-atleast-1d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.atleast_1d">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">atleast_1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.atleast_1d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">atleast_1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.atleast_1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a 1-dimensional view of each input tensor with zero dimensions.
 Input tensors with one or more dimensions are returned as-is.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.atleast_2d.html b/2.9/generated/torch.atleast_2d.html
index c2a56479aa3..34ff1f2bb67 100644
--- a/2.9/generated/torch.atleast_2d.html
+++ b/2.9/generated/torch.atleast_2d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.atleast_2d<a class="headerlink" href="#torch-atleast-2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.atleast_2d">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">atleast_2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.atleast_2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">atleast_2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.atleast_2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a 2-dimensional view of each input tensor with zero dimensions.
 Input tensors with two or more dimensions are returned as-is.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.atleast_3d.html b/2.9/generated/torch.atleast_3d.html
index cf362ef2dad..d9f3d431f85 100644
--- a/2.9/generated/torch.atleast_3d.html
+++ b/2.9/generated/torch.atleast_3d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.atleast_3d<a class="headerlink" href="#torch-atleast-3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.atleast_3d">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">atleast_3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1548"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.atleast_3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">atleast_3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1548"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.atleast_3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a 3-dimensional view of each input tensor with zero dimensions.
 Input tensors with three or more dimensions are returned as-is.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.autograd.Function.backward.html b/2.9/generated/torch.autograd.Function.backward.html
index 9554faadfa5..fdc1c3c57da 100644
--- a/2.9/generated/torch.autograd.Function.backward.html
+++ b/2.9/generated/torch.autograd.Function.backward.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.Function.backward<a class="headerlink" href="#torch-autograd-function-backward" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.Function.backward">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Function.</span></span><span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_outputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function.backward" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Function.</span></span><span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_outputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function.backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a formula for differentiating the operation with backward mode automatic differentiation.</p>
 <p>This function is to be overridden by all subclasses.
 (Defining this function is equivalent to defining the <code class="docutils literal notranslate"><span class="pre">vjp</span></code> function.)</p>
diff --git a/2.9/generated/torch.autograd.Function.forward.html b/2.9/generated/torch.autograd.Function.forward.html
index 8914dcaceb9..a3e3adc9984 100644
--- a/2.9/generated/torch.autograd.Function.forward.html
+++ b/2.9/generated/torch.autograd.Function.forward.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.Function.forward<a class="headerlink" href="#torch-autograd-function-forward" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.Function.forward">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Function.</span></span><span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L350"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function.forward" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Function.</span></span><span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L350"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Define the forward of the custom autograd Function.</p>
 <p>This function is to be overridden by all subclasses.
 There are two ways to define forward:</p>
diff --git a/2.9/generated/torch.autograd.Function.jvp.html b/2.9/generated/torch.autograd.Function.jvp.html
index a039c60e308..a68df6f45fc 100644
--- a/2.9/generated/torch.autograd.Function.jvp.html
+++ b/2.9/generated/torch.autograd.Function.jvp.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.Function.jvp<a class="headerlink" href="#torch-autograd-function-jvp" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.Function.jvp">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Function.</span></span><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_inputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function.jvp" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Function.</span></span><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_inputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function.jvp" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a formula for differentiating the operation with forward mode automatic differentiation.</p>
 <p>This function is to be overridden by all subclasses.
 It must accept a context <code class="xref py py-attr docutils literal notranslate"><span class="pre">ctx</span></code> as the first argument, followed by
diff --git a/2.9/generated/torch.autograd.Function.vmap.html b/2.9/generated/torch.autograd.Function.vmap.html
index b4cd5b4c386..f5b2d394bf6 100644
--- a/2.9/generated/torch.autograd.Function.vmap.html
+++ b/2.9/generated/torch.autograd.Function.vmap.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.Function.vmap<a class="headerlink" href="#torch-autograd-function-vmap" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.Function.vmap">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Function.</span></span><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function.vmap" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Function.</span></span><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.Function.vmap" title="Permalink to this definition">#</a></dt>
 <dd><p>Define the behavior for this autograd.Function underneath <a class="reference internal" href="torch.vmap.html#torch.vmap" title="torch.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.vmap()</span></code></a>.</p>
 <p>For a <a class="reference internal" href="../autograd.html#torch.autograd.Function" title="torch.autograd.Function"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.autograd.Function()</span></code></a> to support
 <a class="reference internal" href="torch.vmap.html#torch.vmap" title="torch.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.vmap()</span></code></a>, you must either override this static method, or set
diff --git a/2.9/generated/torch.autograd.backward.html b/2.9/generated/torch.autograd.backward.html
index b3166b8aa41..eb30a633df5 100644
--- a/2.9/generated/torch.autograd.backward.html
+++ b/2.9/generated/torch.autograd.backward.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.backward<a class="headerlink" href="#torch-autograd-backward" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.backward">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_variables</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/__init__.py#L243"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_variables</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/__init__.py#L243"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the sum of gradients of given tensors with respect to graph leaves.</p>
 <p>The graph is differentiated using the chain rule. If any of <code class="docutils literal notranslate"><span class="pre">tensors</span></code>
 are non-scalar (i.e. their data has more than one element) and require
diff --git a/2.9/generated/torch.autograd.forward_ad.UnpackedDualTensor.html b/2.9/generated/torch.autograd.forward_ad.UnpackedDualTensor.html
index 67750d9c5ec..6b7deff0231 100644
--- a/2.9/generated/torch.autograd.forward_ad.UnpackedDualTensor.html
+++ b/2.9/generated/torch.autograd.forward_ad.UnpackedDualTensor.html
@@ -4404,7 +4404,7 @@
 <h1>UnpackedDualTensor<a class="headerlink" href="#unpackeddualtensor" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.forward_ad.UnpackedDualTensor">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">UnpackedDualTensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">primal</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tangent</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/forward_ad.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.UnpackedDualTensor" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">UnpackedDualTensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">primal</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tangent</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/forward_ad.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.UnpackedDualTensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Namedtuple returned by <a class="reference internal" href="torch.autograd.forward_ad.unpack_dual.html#torch.autograd.forward_ad.unpack_dual" title="torch.autograd.forward_ad.unpack_dual"><code class="xref py py-func docutils literal notranslate"><span class="pre">unpack_dual()</span></code></a> containing the primal and tangent components of the dual tensor.</p>
 <p>See <a class="reference internal" href="torch.autograd.forward_ad.unpack_dual.html#torch.autograd.forward_ad.unpack_dual" title="torch.autograd.forward_ad.unpack_dual"><code class="xref py py-func docutils literal notranslate"><span class="pre">unpack_dual()</span></code></a> for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.autograd.forward_ad.dual_level.html b/2.9/generated/torch.autograd.forward_ad.dual_level.html
index 821b0b9b120..358cb22ead1 100644
--- a/2.9/generated/torch.autograd.forward_ad.dual_level.html
+++ b/2.9/generated/torch.autograd.forward_ad.dual_level.html
@@ -4404,7 +4404,7 @@
 <h1>dual_level<a class="headerlink" href="#dual-level" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.forward_ad.dual_level">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">dual_level</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/forward_ad.py#L173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.dual_level" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">dual_level</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/forward_ad.py#L173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.dual_level" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager for forward AD, where all forward AD computation must occur within the <code class="docutils literal notranslate"><span class="pre">dual_level</span></code> context.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.autograd.forward_ad.enter_dual_level.html b/2.9/generated/torch.autograd.forward_ad.enter_dual_level.html
index f25d01c5be4..3c2ce7a9dde 100644
--- a/2.9/generated/torch.autograd.forward_ad.enter_dual_level.html
+++ b/2.9/generated/torch.autograd.forward_ad.enter_dual_level.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.forward_ad.enter_dual_level<a class="headerlink" href="#torch-autograd-forward-ad-enter-dual-level" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.forward_ad.enter_dual_level">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">enter_dual_level</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/forward_ad.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.enter_dual_level" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">enter_dual_level</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/forward_ad.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.enter_dual_level" title="Permalink to this definition">#</a></dt>
 <dd><p>Enter a new forward grad level.</p>
 <p>This level can be used to make and unpack dual Tensors to compute
 forward gradients.</p>
diff --git a/2.9/generated/torch.autograd.forward_ad.exit_dual_level.html b/2.9/generated/torch.autograd.forward_ad.exit_dual_level.html
index 721bf271bf7..6823dba93a2 100644
--- a/2.9/generated/torch.autograd.forward_ad.exit_dual_level.html
+++ b/2.9/generated/torch.autograd.forward_ad.exit_dual_level.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.forward_ad.exit_dual_level<a class="headerlink" href="#torch-autograd-forward-ad-exit-dual-level" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.forward_ad.exit_dual_level">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">exit_dual_level</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/forward_ad.py#L43"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.exit_dual_level" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">exit_dual_level</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/forward_ad.py#L43"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.exit_dual_level" title="Permalink to this definition">#</a></dt>
 <dd><p>Exit a forward grad level.</p>
 <p>This function deletes all the gradients associated with this
 level. Only deleting the latest entered level is allowed.</p>
diff --git a/2.9/generated/torch.autograd.forward_ad.make_dual.html b/2.9/generated/torch.autograd.forward_ad.make_dual.html
index 9776e7765be..338add34df7 100644
--- a/2.9/generated/torch.autograd.forward_ad.make_dual.html
+++ b/2.9/generated/torch.autograd.forward_ad.make_dual.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.forward_ad.make_dual<a class="headerlink" href="#torch-autograd-forward-ad-make-dual" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.forward_ad.make_dual">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">make_dual</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tangent</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/forward_ad.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.make_dual" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">make_dual</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tangent</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/forward_ad.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.make_dual" title="Permalink to this definition">#</a></dt>
 <dd><p>Associate a tensor value with its tangent to create a “dual tensor” for forward AD gradient computation.</p>
 <p>The result is a new tensor aliased to <code class="xref py py-attr docutils literal notranslate"><span class="pre">tensor</span></code> with <code class="xref py py-attr docutils literal notranslate"><span class="pre">tangent</span></code> embedded
 as an attribute as-is if it has the same storage layout or copied otherwise.
diff --git a/2.9/generated/torch.autograd.forward_ad.unpack_dual.html b/2.9/generated/torch.autograd.forward_ad.unpack_dual.html
index e58e299a8b4..dd46bb5b411 100644
--- a/2.9/generated/torch.autograd.forward_ad.unpack_dual.html
+++ b/2.9/generated/torch.autograd.forward_ad.unpack_dual.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.forward_ad.unpack_dual<a class="headerlink" href="#torch-autograd-forward-ad-unpack-dual" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.forward_ad.unpack_dual">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">unpack_dual</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/forward_ad.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.unpack_dual" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.forward_ad.</span></span><span class="sig-name descname"><span class="pre">unpack_dual</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/forward_ad.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.forward_ad.unpack_dual" title="Permalink to this definition">#</a></dt>
 <dd><p>Unpack a “dual tensor” to get both its Tensor value and its forward AD gradient.</p>
 <p>The result is a namedtuple <code class="docutils literal notranslate"><span class="pre">(primal,</span> <span class="pre">tangent)</span></code> where <code class="docutils literal notranslate"><span class="pre">primal</span></code> is a view of
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">tensor</span></code>’s primal and <code class="docutils literal notranslate"><span class="pre">tangent</span></code> is <code class="xref py py-attr docutils literal notranslate"><span class="pre">tensor</span></code>’s tangent as-is.
diff --git a/2.9/generated/torch.autograd.function.BackwardCFunction.html b/2.9/generated/torch.autograd.function.BackwardCFunction.html
index cf6f516c2ba..55c20fd8165 100644
--- a/2.9/generated/torch.autograd.function.BackwardCFunction.html
+++ b/2.9/generated/torch.autograd.function.BackwardCFunction.html
@@ -4404,23 +4404,23 @@
 <h1>BackwardCFunction<a class="headerlink" href="#backwardcfunction" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.function.BackwardCFunction">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.function.</span></span><span class="sig-name descname"><span class="pre">BackwardCFunction</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.function.</span></span><span class="sig-name descname"><span class="pre">BackwardCFunction</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction" title="Permalink to this definition">#</a></dt>
 <dd><p>This class is used for internal autograd work. Do not use.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.BackwardCFunction.apply">
-<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.apply" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply method used when executing this Node during the backward</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.BackwardCFunction.apply_jvp">
-<span class="sig-name descname"><span class="pre">apply_jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.apply_jvp" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.apply_jvp" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply method used when executing forward mode AD during the forward</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.BackwardCFunction.mark_dirty">
-<span class="sig-name descname"><span class="pre">mark_dirty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.mark_dirty" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mark_dirty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.mark_dirty" title="Permalink to this definition">#</a></dt>
 <dd><p>Mark given tensors as modified in an in-place operation.</p>
 <p>This should be called at most once, in either the <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code>
 or <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods, and all arguments should be inputs.</p>
@@ -4458,7 +4458,7 @@ <h1>BackwardCFunction<a class="headerlink" href="#backwardcfunction" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.BackwardCFunction.mark_non_differentiable">
-<span class="sig-name descname"><span class="pre">mark_non_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.mark_non_differentiable" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mark_non_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.mark_non_differentiable" title="Permalink to this definition">#</a></dt>
 <dd><p>Mark outputs as non-differentiable.</p>
 <p>This should be called at most once, in either the <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code>
 or <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods, and all arguments should be tensor outputs.</p>
@@ -4493,7 +4493,7 @@ <h1>BackwardCFunction<a class="headerlink" href="#backwardcfunction" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.BackwardCFunction.save_for_backward">
-<span class="sig-name descname"><span class="pre">save_for_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.save_for_backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_for_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.save_for_backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Save given tensors for a future call to <code class="xref py py-func docutils literal notranslate"><span class="pre">backward()</span></code>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">save_for_backward</span></code> should be called at most once, in either the
 <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code> or <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods, and only with tensors.</p>
@@ -4549,7 +4549,7 @@ <h1>BackwardCFunction<a class="headerlink" href="#backwardcfunction" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.BackwardCFunction.save_for_forward">
-<span class="sig-name descname"><span class="pre">save_for_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.save_for_forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_for_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.save_for_forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Save given tensors for a future call to <code class="xref py py-func docutils literal notranslate"><span class="pre">jvp()</span></code>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">save_for_forward</span></code> should be called at most once, in either the
 <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code> or <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods, and all arguments
@@ -4595,7 +4595,7 @@ <h1>BackwardCFunction<a class="headerlink" href="#backwardcfunction" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.BackwardCFunction.set_materialize_grads">
-<span class="sig-name descname"><span class="pre">set_materialize_grads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.set_materialize_grads" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_materialize_grads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.BackwardCFunction.set_materialize_grads" title="Permalink to this definition">#</a></dt>
 <dd><p>Set whether to materialize grad tensors. Default is <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
 <p>This should be called only from either the <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code> or
 <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods.</p>
diff --git a/2.9/generated/torch.autograd.function.FunctionCtx.mark_dirty.html b/2.9/generated/torch.autograd.function.FunctionCtx.mark_dirty.html
index 2e9a9f22dbe..eed17af9c67 100644
--- a/2.9/generated/torch.autograd.function.FunctionCtx.mark_dirty.html
+++ b/2.9/generated/torch.autograd.function.FunctionCtx.mark_dirty.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.function.FunctionCtx.mark_dirty<a class="headerlink" href="#torch-autograd-function-functionctx-mark-dirty" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.FunctionCtx.mark_dirty">
-<span class="sig-prename descclassname"><span class="pre">FunctionCtx.</span></span><span class="sig-name descname"><span class="pre">mark_dirty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.FunctionCtx.mark_dirty" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">FunctionCtx.</span></span><span class="sig-name descname"><span class="pre">mark_dirty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.FunctionCtx.mark_dirty" title="Permalink to this definition">#</a></dt>
 <dd><p>Mark given tensors as modified in an in-place operation.</p>
 <p>This should be called at most once, in either the <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code>
 or <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods, and all arguments should be inputs.</p>
diff --git a/2.9/generated/torch.autograd.function.FunctionCtx.mark_non_differentiable.html b/2.9/generated/torch.autograd.function.FunctionCtx.mark_non_differentiable.html
index 6bf46e10ba3..e6191ac9da9 100644
--- a/2.9/generated/torch.autograd.function.FunctionCtx.mark_non_differentiable.html
+++ b/2.9/generated/torch.autograd.function.FunctionCtx.mark_non_differentiable.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.function.FunctionCtx.mark_non_differentiable<a class="headerlink" href="#torch-autograd-function-functionctx-mark-non-differentiable" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.FunctionCtx.mark_non_differentiable">
-<span class="sig-prename descclassname"><span class="pre">FunctionCtx.</span></span><span class="sig-name descname"><span class="pre">mark_non_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.FunctionCtx.mark_non_differentiable" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">FunctionCtx.</span></span><span class="sig-name descname"><span class="pre">mark_non_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.FunctionCtx.mark_non_differentiable" title="Permalink to this definition">#</a></dt>
 <dd><p>Mark outputs as non-differentiable.</p>
 <p>This should be called at most once, in either the <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code>
 or <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods, and all arguments should be tensor outputs.</p>
diff --git a/2.9/generated/torch.autograd.function.FunctionCtx.save_for_backward.html b/2.9/generated/torch.autograd.function.FunctionCtx.save_for_backward.html
index 9ac82633796..52e9eeb6e10 100644
--- a/2.9/generated/torch.autograd.function.FunctionCtx.save_for_backward.html
+++ b/2.9/generated/torch.autograd.function.FunctionCtx.save_for_backward.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.function.FunctionCtx.save_for_backward<a class="headerlink" href="#torch-autograd-function-functionctx-save-for-backward" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.FunctionCtx.save_for_backward">
-<span class="sig-prename descclassname"><span class="pre">FunctionCtx.</span></span><span class="sig-name descname"><span class="pre">save_for_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.FunctionCtx.save_for_backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">FunctionCtx.</span></span><span class="sig-name descname"><span class="pre">save_for_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.FunctionCtx.save_for_backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Save given tensors for a future call to <code class="xref py py-func docutils literal notranslate"><span class="pre">backward()</span></code>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">save_for_backward</span></code> should be called at most once, in either the
 <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code> or <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods, and only with tensors.</p>
diff --git a/2.9/generated/torch.autograd.function.FunctionCtx.set_materialize_grads.html b/2.9/generated/torch.autograd.function.FunctionCtx.set_materialize_grads.html
index d86f66a6975..6df79dfbcaa 100644
--- a/2.9/generated/torch.autograd.function.FunctionCtx.set_materialize_grads.html
+++ b/2.9/generated/torch.autograd.function.FunctionCtx.set_materialize_grads.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.function.FunctionCtx.set_materialize_grads<a class="headerlink" href="#torch-autograd-function-functionctx-set-materialize-grads" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.FunctionCtx.set_materialize_grads">
-<span class="sig-prename descclassname"><span class="pre">FunctionCtx.</span></span><span class="sig-name descname"><span class="pre">set_materialize_grads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.FunctionCtx.set_materialize_grads" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">FunctionCtx.</span></span><span class="sig-name descname"><span class="pre">set_materialize_grads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.FunctionCtx.set_materialize_grads" title="Permalink to this definition">#</a></dt>
 <dd><p>Set whether to materialize grad tensors. Default is <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
 <p>This should be called only from either the <code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code> or
 <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> methods.</p>
diff --git a/2.9/generated/torch.autograd.function.InplaceFunction.html b/2.9/generated/torch.autograd.function.InplaceFunction.html
index 86181f4d1a3..1ca5fecf84a 100644
--- a/2.9/generated/torch.autograd.function.InplaceFunction.html
+++ b/2.9/generated/torch.autograd.function.InplaceFunction.html
@@ -4404,12 +4404,12 @@
 <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.function.</span></span><span class="sig-name descname"><span class="pre">InplaceFunction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L653"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.function.</span></span><span class="sig-name descname"><span class="pre">InplaceFunction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L653"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction" title="Permalink to this definition">#</a></dt>
 <dd><p>This class is here only for backward compatibility reasons.
 Use <a class="reference internal" href="../autograd.html#torch.autograd.Function" title="torch.autograd.function.Function"><code class="xref py py-class docutils literal notranslate"><span class="pre">Function</span></code></a> instead of this for any new use case.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.backward">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_outputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.backward" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_outputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a formula for differentiating the operation with backward mode automatic differentiation.</p>
 <p>This function is to be overridden by all subclasses.
 (Defining this function is equivalent to defining the <code class="docutils literal notranslate"><span class="pre">vjp</span></code> function.)</p>
@@ -4436,7 +4436,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.forward">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L350"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.forward" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L350"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Define the forward of the custom autograd Function.</p>
 <p>This function is to be overridden by all subclasses.
 There are two ways to define forward:</p>
@@ -4486,7 +4486,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.jvp">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_inputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.jvp" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_inputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.jvp" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a formula for differentiating the operation with forward mode automatic differentiation.</p>
 <p>This function is to be overridden by all subclasses.
 It must accept a context <code class="xref py py-attr docutils literal notranslate"><span class="pre">ctx</span></code> as the first argument, followed by
@@ -4509,7 +4509,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.mark_dirty">
-<span class="sig-name descname"><span class="pre">mark_dirty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.mark_dirty" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mark_dirty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.mark_dirty" title="Permalink to this definition">#</a></dt>
 <dd><p>Mark given tensors as modified in an in-place operation.</p>
 <p>This should be called at most once, in either the <a class="reference internal" href="#torch.autograd.function.InplaceFunction.setup_context" title="torch.autograd.function.InplaceFunction.setup_context"><code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code></a>
 or <a class="reference internal" href="#torch.autograd.function.InplaceFunction.forward" title="torch.autograd.function.InplaceFunction.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> methods, and all arguments should be inputs.</p>
@@ -4547,7 +4547,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.mark_non_differentiable">
-<span class="sig-name descname"><span class="pre">mark_non_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.mark_non_differentiable" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mark_non_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.mark_non_differentiable" title="Permalink to this definition">#</a></dt>
 <dd><p>Mark outputs as non-differentiable.</p>
 <p>This should be called at most once, in either the <a class="reference internal" href="#torch.autograd.function.InplaceFunction.setup_context" title="torch.autograd.function.InplaceFunction.setup_context"><code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code></a>
 or <a class="reference internal" href="#torch.autograd.function.InplaceFunction.forward" title="torch.autograd.function.InplaceFunction.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> methods, and all arguments should be tensor outputs.</p>
@@ -4582,7 +4582,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.save_for_backward">
-<span class="sig-name descname"><span class="pre">save_for_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.save_for_backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_for_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.save_for_backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Save given tensors for a future call to <code class="xref py py-func docutils literal notranslate"><span class="pre">backward()</span></code>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">save_for_backward</span></code> should be called at most once, in either the
 <a class="reference internal" href="#torch.autograd.function.InplaceFunction.setup_context" title="torch.autograd.function.InplaceFunction.setup_context"><code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code></a> or <a class="reference internal" href="#torch.autograd.function.InplaceFunction.forward" title="torch.autograd.function.InplaceFunction.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> methods, and only with tensors.</p>
@@ -4638,7 +4638,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.save_for_forward">
-<span class="sig-name descname"><span class="pre">save_for_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.save_for_forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_for_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.save_for_forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Save given tensors for a future call to <code class="xref py py-func docutils literal notranslate"><span class="pre">jvp()</span></code>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">save_for_forward</span></code> should be called at most once, in either the
 <a class="reference internal" href="#torch.autograd.function.InplaceFunction.setup_context" title="torch.autograd.function.InplaceFunction.setup_context"><code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code></a> or <a class="reference internal" href="#torch.autograd.function.InplaceFunction.forward" title="torch.autograd.function.InplaceFunction.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> methods, and all arguments
@@ -4684,7 +4684,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.set_materialize_grads">
-<span class="sig-name descname"><span class="pre">set_materialize_grads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.set_materialize_grads" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_materialize_grads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.set_materialize_grads" title="Permalink to this definition">#</a></dt>
 <dd><p>Set whether to materialize grad tensors. Default is <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
 <p>This should be called only from either the <a class="reference internal" href="#torch.autograd.function.InplaceFunction.setup_context" title="torch.autograd.function.InplaceFunction.setup_context"><code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code></a> or
 <a class="reference internal" href="#torch.autograd.function.InplaceFunction.forward" title="torch.autograd.function.InplaceFunction.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> methods.</p>
@@ -4730,7 +4730,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.setup_context">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">setup_context</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.setup_context" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">setup_context</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.setup_context" title="Permalink to this definition">#</a></dt>
 <dd><p>There are two ways to define the forward pass of an autograd.Function.</p>
 <p>Either:</p>
 <ol class="arabic simple">
@@ -4751,7 +4751,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.vjp">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vjp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_outputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.vjp" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vjp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_outputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.vjp" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a formula for differentiating the operation with backward mode automatic differentiation.</p>
 <p>This function is to be overridden by all subclasses.
 (Defining this function is equivalent to defining the <code class="docutils literal notranslate"><span class="pre">vjp</span></code> function.)</p>
@@ -4778,7 +4778,7 @@ <h1>InplaceFunction<a class="headerlink" href="#inplacefunction" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.InplaceFunction.vmap">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.vmap" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.InplaceFunction.vmap" title="Permalink to this definition">#</a></dt>
 <dd><p>Define the behavior for this autograd.Function underneath <a class="reference internal" href="torch.vmap.html#torch.vmap" title="torch.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.vmap()</span></code></a>.</p>
 <p>For a <a class="reference internal" href="../autograd.html#torch.autograd.Function" title="torch.autograd.Function"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.autograd.Function()</span></code></a> to support
 <a class="reference internal" href="torch.vmap.html#torch.vmap" title="torch.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.vmap()</span></code></a>, you must either override this static method, or set
diff --git a/2.9/generated/torch.autograd.function.NestedIOFunction.html b/2.9/generated/torch.autograd.function.NestedIOFunction.html
index 1eb59b2aed2..95ed10b2a18 100644
--- a/2.9/generated/torch.autograd.function.NestedIOFunction.html
+++ b/2.9/generated/torch.autograd.function.NestedIOFunction.html
@@ -4404,12 +4404,12 @@
 <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.function.</span></span><span class="sig-name descname"><span class="pre">NestedIOFunction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L773"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.function.</span></span><span class="sig-name descname"><span class="pre">NestedIOFunction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L773"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction" title="Permalink to this definition">#</a></dt>
 <dd><p>This class is here only for backward compatibility reasons.
 Use <a class="reference internal" href="../autograd.html#torch.autograd.Function" title="torch.autograd.function.Function"><code class="xref py py-class docutils literal notranslate"><span class="pre">Function</span></code></a> instead of this for any new use case.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.backward">
-<span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">gradients</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L797"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">gradients</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L797"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.backward" title="Permalink to this definition">#</a></dt>
 <dd><p>Shared backward utility.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4420,7 +4420,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.backward_extended">
-<span class="sig-name descname"><span class="pre">backward_extended</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_output</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L850"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.backward_extended" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">backward_extended</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_output</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L850"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.backward_extended" title="Permalink to this definition">#</a></dt>
 <dd><p>User defined backward.</p>
 <dl class="field-list simple">
 </dl>
@@ -4428,7 +4428,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Shared forward utility.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4439,7 +4439,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.forward_extended">
-<span class="sig-name descname"><span class="pre">forward_extended</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L844"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.forward_extended" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward_extended</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L844"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.forward_extended" title="Permalink to this definition">#</a></dt>
 <dd><p>User defined forward.</p>
 <dl class="field-list simple">
 </dl>
@@ -4447,7 +4447,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.jvp">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_inputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.jvp" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_inputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.jvp" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a formula for differentiating the operation with forward mode automatic differentiation.</p>
 <p>This function is to be overridden by all subclasses.
 It must accept a context <code class="xref py py-attr docutils literal notranslate"><span class="pre">ctx</span></code> as the first argument, followed by
@@ -4470,7 +4470,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.mark_dirty">
-<span class="sig-name descname"><span class="pre">mark_dirty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L832"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.mark_dirty" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mark_dirty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L832"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.mark_dirty" title="Permalink to this definition">#</a></dt>
 <dd><p>See <code class="xref py py-meth docutils literal notranslate"><span class="pre">Function.mark_dirty()</span></code>.</p>
 <dl class="field-list simple">
 </dl>
@@ -4478,7 +4478,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.mark_non_differentiable">
-<span class="sig-name descname"><span class="pre">mark_non_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L838"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.mark_non_differentiable" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mark_non_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L838"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.mark_non_differentiable" title="Permalink to this definition">#</a></dt>
 <dd><p>See <code class="xref py py-meth docutils literal notranslate"><span class="pre">Function.mark_non_differentiable()</span></code>.</p>
 <dl class="field-list simple">
 </dl>
@@ -4486,7 +4486,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.save_for_backward">
-<span class="sig-name descname"><span class="pre">save_for_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.save_for_backward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_for_backward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.save_for_backward" title="Permalink to this definition">#</a></dt>
 <dd><p>See <code class="xref py py-meth docutils literal notranslate"><span class="pre">Function.save_for_backward()</span></code>.</p>
 <dl class="field-list simple">
 </dl>
@@ -4494,7 +4494,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.save_for_forward">
-<span class="sig-name descname"><span class="pre">save_for_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.save_for_forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_for_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L100"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.save_for_forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Save given tensors for a future call to <code class="xref py py-func docutils literal notranslate"><span class="pre">jvp()</span></code>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">save_for_forward</span></code> should be called at most once, in either the
 <a class="reference internal" href="#torch.autograd.function.NestedIOFunction.setup_context" title="torch.autograd.function.NestedIOFunction.setup_context"><code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code></a> or <a class="reference internal" href="#torch.autograd.function.NestedIOFunction.forward" title="torch.autograd.function.NestedIOFunction.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> methods, and all arguments
@@ -4546,7 +4546,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.set_materialize_grads">
-<span class="sig-name descname"><span class="pre">set_materialize_grads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.set_materialize_grads" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_materialize_grads</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.set_materialize_grads" title="Permalink to this definition">#</a></dt>
 <dd><p>Set whether to materialize grad tensors. Default is <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
 <p>This should be called only from either the <a class="reference internal" href="#torch.autograd.function.NestedIOFunction.setup_context" title="torch.autograd.function.NestedIOFunction.setup_context"><code class="xref py py-func docutils literal notranslate"><span class="pre">setup_context()</span></code></a> or
 <a class="reference internal" href="#torch.autograd.function.NestedIOFunction.forward" title="torch.autograd.function.NestedIOFunction.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> methods.</p>
@@ -4592,7 +4592,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.setup_context">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">setup_context</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.setup_context" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">setup_context</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.setup_context" title="Permalink to this definition">#</a></dt>
 <dd><p>There are two ways to define the forward pass of an autograd.Function.</p>
 <p>Either:</p>
 <ol class="arabic simple">
@@ -4613,7 +4613,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.vjp">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vjp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_outputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.vjp" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vjp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ctx</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">grad_outputs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.vjp" title="Permalink to this definition">#</a></dt>
 <dd><p>Define a formula for differentiating the operation with backward mode automatic differentiation.</p>
 <p>This function is to be overridden by all subclasses.
 (Defining this function is equivalent to defining the <code class="docutils literal notranslate"><span class="pre">vjp</span></code> function.)</p>
@@ -4640,7 +4640,7 @@ <h1>NestedIOFunction<a class="headerlink" href="#nestediofunction" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.function.NestedIOFunction.vmap">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.vmap" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.NestedIOFunction.vmap" title="Permalink to this definition">#</a></dt>
 <dd><p>Define the behavior for this autograd.Function underneath <a class="reference internal" href="torch.vmap.html#torch.vmap" title="torch.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.vmap()</span></code></a>.</p>
 <p>For a <a class="reference internal" href="../autograd.html#torch.autograd.Function" title="torch.autograd.Function"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.autograd.Function()</span></code></a> to support
 <a class="reference internal" href="torch.vmap.html#torch.vmap" title="torch.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.vmap()</span></code></a>, you must either override this static method, or set
diff --git a/2.9/generated/torch.autograd.function.once_differentiable.html b/2.9/generated/torch.autograd.function.once_differentiable.html
index 3419e48905c..f383b912c14 100644
--- a/2.9/generated/torch.autograd.function.once_differentiable.html
+++ b/2.9/generated/torch.autograd.function.once_differentiable.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.function.once_differentiable<a class="headerlink" href="#torch-autograd-function-once-differentiable" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.function.once_differentiable">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.function.</span></span><span class="sig-name descname"><span class="pre">once_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/function.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.once_differentiable" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.function.</span></span><span class="sig-name descname"><span class="pre">once_differentiable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/function.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.function.once_differentiable" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><em>Callable</em></a>[[<em>Concatenate</em>[<em>_T</em>, ~_P]], <em>_R</em>]</p>
diff --git a/2.9/generated/torch.autograd.functional.hessian.html b/2.9/generated/torch.autograd.functional.hessian.html
index 09f0571bec1..de4c5b47be4 100644
--- a/2.9/generated/torch.autograd.functional.hessian.html
+++ b/2.9/generated/torch.autograd.functional.hessian.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.functional.hessian<a class="headerlink" href="#torch-autograd-functional-hessian" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.functional.hessian">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">hessian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vectorize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">outer_jacobian_strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reverse-mode'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/functional.py#L841"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.hessian" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">hessian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vectorize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">outer_jacobian_strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reverse-mode'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/functional.py#L841"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.hessian" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the Hessian of a given scalar function.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.autograd.functional.hvp.html b/2.9/generated/torch.autograd.functional.hvp.html
index 003b40b6438..c75e69afa4e 100644
--- a/2.9/generated/torch.autograd.functional.hvp.html
+++ b/2.9/generated/torch.autograd.functional.hvp.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.functional.hvp<a class="headerlink" href="#torch-autograd-functional-hvp" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.functional.hvp">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">hvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/functional.py#L1080"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.hvp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">hvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/functional.py#L1080"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.hvp" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the dot product between the scalar function’s Hessian and a vector <code class="docutils literal notranslate"><span class="pre">v</span></code> at a specified point.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.autograd.functional.jacobian.html b/2.9/generated/torch.autograd.functional.jacobian.html
index 6e7951de0d9..67777cccdd6 100644
--- a/2.9/generated/torch.autograd.functional.jacobian.html
+++ b/2.9/generated/torch.autograd.functional.jacobian.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.functional.jacobian<a class="headerlink" href="#torch-autograd-functional-jacobian" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.functional.jacobian">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">jacobian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vectorize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reverse-mode'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/functional.py#L574"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.jacobian" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">jacobian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vectorize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reverse-mode'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/functional.py#L574"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.jacobian" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the Jacobian of a given function.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.autograd.functional.jvp.html b/2.9/generated/torch.autograd.functional.jvp.html
index 78703d75714..479aac7a5e0 100644
--- a/2.9/generated/torch.autograd.functional.jvp.html
+++ b/2.9/generated/torch.autograd.functional.jvp.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.functional.jvp<a class="headerlink" href="#torch-autograd-functional-jvp" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.functional.jvp">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/functional.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.jvp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/functional.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.jvp" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the dot product between the Jacobian of the given function at the point given by the inputs and a vector <code class="docutils literal notranslate"><span class="pre">v</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.autograd.functional.vhp.html b/2.9/generated/torch.autograd.functional.vhp.html
index c01ee897dca..453fbbeccc5 100644
--- a/2.9/generated/torch.autograd.functional.vhp.html
+++ b/2.9/generated/torch.autograd.functional.vhp.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.functional.vhp<a class="headerlink" href="#torch-autograd-functional-vhp" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.functional.vhp">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">vhp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/functional.py#L979"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.vhp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">vhp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/functional.py#L979"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.vhp" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the dot product between vector <code class="docutils literal notranslate"><span class="pre">v</span></code> and Hessian of a  given scalar function at a specified point.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.autograd.functional.vjp.html b/2.9/generated/torch.autograd.functional.vjp.html
index dd4e05fa78d..7f1e1bb578e 100644
--- a/2.9/generated/torch.autograd.functional.vjp.html
+++ b/2.9/generated/torch.autograd.functional.vjp.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.functional.vjp<a class="headerlink" href="#torch-autograd-functional-vjp" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.functional.vjp">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">vjp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/functional.py#L263"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.vjp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.functional.</span></span><span class="sig-name descname"><span class="pre">vjp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/functional.py#L263"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.functional.vjp" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the dot product between a vector <code class="docutils literal notranslate"><span class="pre">v</span></code> and the Jacobian of the given function at the point given by the inputs.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.autograd.grad.html b/2.9/generated/torch.autograd.grad.html
index 5e60deb0e73..a35d7508201 100644
--- a/2.9/generated/torch.autograd.grad.html
+++ b/2.9/generated/torch.autograd.grad.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.grad<a class="headerlink" href="#torch-autograd-grad" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.grad">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">outputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_outputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">only_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_unused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_grads_batched</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">materialize_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/__init__.py#L365"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.</span></span><span class="sig-name descname"><span class="pre">grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">outputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_outputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">retain_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">create_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">only_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_unused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_grads_batched</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">materialize_grads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/__init__.py#L365"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and return the sum of gradients of outputs with respect to the inputs.</p>
 <p><code class="docutils literal notranslate"><span class="pre">grad_outputs</span></code> should be a sequence of length matching <code class="docutils literal notranslate"><span class="pre">output</span></code>
 containing the “vector” in vector-Jacobian product, usually the pre-computed
diff --git a/2.9/generated/torch.autograd.grad_mode.inference_mode.html b/2.9/generated/torch.autograd.grad_mode.inference_mode.html
index 3da80220333..04b11bb2d56 100644
--- a/2.9/generated/torch.autograd.grad_mode.inference_mode.html
+++ b/2.9/generated/torch.autograd.grad_mode.inference_mode.html
@@ -4404,7 +4404,7 @@
 <h1>inference_mode<a class="headerlink" href="#inference-mode" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.grad_mode.inference_mode">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.grad_mode.</span></span><span class="sig-name descname"><span class="pre">inference_mode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/grad_mode.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.inference_mode" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.grad_mode.</span></span><span class="sig-name descname"><span class="pre">inference_mode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/grad_mode.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.inference_mode" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager that enables or disables inference mode.</p>
 <p>InferenceMode is analogous to <a class="reference internal" href="torch.no_grad.html#torch.no_grad" title="torch.autograd.grad_mode.no_grad"><code class="xref py py-class docutils literal notranslate"><span class="pre">no_grad</span></code></a> and should be used
 when you are certain your operations will not interact with autograd
@@ -4466,7 +4466,7 @@ <h1>inference_mode<a class="headerlink" href="#inference-mode" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.grad_mode.inference_mode.clone">
-<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/grad_mode.py#L290"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.inference_mode.clone" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/grad_mode.py#L290"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.inference_mode.clone" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a copy of this class</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.autograd.grad_mode.set_grad_enabled.html b/2.9/generated/torch.autograd.grad_mode.set_grad_enabled.html
index d9d70a6a7ee..fc0e9a5785f 100644
--- a/2.9/generated/torch.autograd.grad_mode.set_grad_enabled.html
+++ b/2.9/generated/torch.autograd.grad_mode.set_grad_enabled.html
@@ -4404,7 +4404,7 @@
 <h1>set_grad_enabled<a class="headerlink" href="#set-grad-enabled" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.grad_mode.set_grad_enabled">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.grad_mode.</span></span><span class="sig-name descname"><span class="pre">set_grad_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/grad_mode.py#L143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.set_grad_enabled" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.grad_mode.</span></span><span class="sig-name descname"><span class="pre">set_grad_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/grad_mode.py#L143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.set_grad_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that sets gradient calculation on or off.</p>
 <p><code class="docutils literal notranslate"><span class="pre">set_grad_enabled</span></code> will enable or disable grads based on its argument <code class="xref py py-attr docutils literal notranslate"><span class="pre">mode</span></code>.
 It can be used as a context-manager or as a function.</p>
@@ -4448,7 +4448,7 @@ <h1>set_grad_enabled<a class="headerlink" href="#set-grad-enabled" title="Permal
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.grad_mode.set_grad_enabled.clone">
-<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/grad_mode.py#L205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.set_grad_enabled.clone" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/grad_mode.py#L205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.set_grad_enabled.clone" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a copy of this class</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.autograd.grad_mode.set_multithreading_enabled.html b/2.9/generated/torch.autograd.grad_mode.set_multithreading_enabled.html
index 23cd3f0df62..a2a91d7423b 100644
--- a/2.9/generated/torch.autograd.grad_mode.set_multithreading_enabled.html
+++ b/2.9/generated/torch.autograd.grad_mode.set_multithreading_enabled.html
@@ -4404,7 +4404,7 @@
 <h1>set_multithreading_enabled<a class="headerlink" href="#set-multithreading-enabled" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.grad_mode.set_multithreading_enabled">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.grad_mode.</span></span><span class="sig-name descname"><span class="pre">set_multithreading_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/grad_mode.py#L307"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.set_multithreading_enabled" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.grad_mode.</span></span><span class="sig-name descname"><span class="pre">set_multithreading_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/grad_mode.py#L307"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.set_multithreading_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that sets multithreaded backwards on or off.</p>
 <p><code class="docutils literal notranslate"><span class="pre">set_multithreading_enabled</span></code> will enable or disable multithreaded backwards based on its argument <code class="xref py py-attr docutils literal notranslate"><span class="pre">mode</span></code>.
 It can be used as a context-manager or as a function.</p>
@@ -4422,7 +4422,7 @@ <h1>set_multithreading_enabled<a class="headerlink" href="#set-multithreading-en
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.grad_mode.set_multithreading_enabled.clone">
-<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/grad_mode.py#L336"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.set_multithreading_enabled.clone" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/grad_mode.py#L336"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.grad_mode.set_multithreading_enabled.clone" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a copy of this class</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.autograd.gradcheck.GradcheckError.html b/2.9/generated/torch.autograd.gradcheck.GradcheckError.html
index 9e84e3121e5..da4cf4a73fd 100644
--- a/2.9/generated/torch.autograd.gradcheck.GradcheckError.html
+++ b/2.9/generated/torch.autograd.gradcheck.GradcheckError.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.gradcheck.GradcheckError<a class="headerlink" href="#torch-autograd-gradcheck-gradcheckerror" title="Permalink to this heading">#</a></h1>
 <dl class="py exception">
 <dt class="sig sig-object py" id="torch.autograd.gradcheck.GradcheckError">
-<em class="property"><span class="pre">exception</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.gradcheck.</span></span><span class="sig-name descname"><span class="pre">GradcheckError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/gradcheck.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.gradcheck.GradcheckError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">exception</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.gradcheck.</span></span><span class="sig-name descname"><span class="pre">GradcheckError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/gradcheck.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.gradcheck.GradcheckError" title="Permalink to this definition">#</a></dt>
 <dd><p>Error raised by <a class="reference internal" href="torch.autograd.gradcheck.gradcheck.html#torch.autograd.gradcheck.gradcheck" title="torch.autograd.gradcheck.gradcheck"><code class="xref py py-func docutils literal notranslate"><span class="pre">gradcheck()</span></code></a> and <a class="reference internal" href="torch.autograd.gradcheck.gradgradcheck.html#torch.autograd.gradcheck.gradgradcheck" title="torch.autograd.gradcheck.gradgradcheck"><code class="xref py py-func docutils literal notranslate"><span class="pre">gradgradcheck()</span></code></a>.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.autograd.gradcheck.gradcheck.html b/2.9/generated/torch.autograd.gradcheck.gradcheck.html
index 84868c7bb17..03bc1f081b9 100644
--- a/2.9/generated/torch.autograd.gradcheck.gradcheck.html
+++ b/2.9/generated/torch.autograd.gradcheck.gradcheck.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.gradcheck.gradcheck<a class="headerlink" href="#torch-autograd-gradcheck-gradcheck" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.gradcheck.gradcheck">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.gradcheck.</span></span><span class="sig-name descname"><span class="pre">gradcheck</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raise_exception</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nondet_tol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_undefined_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_grad_dtypes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_batched_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_batched_forward_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_forward_ad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_backward_ad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fast_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">masked</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/gradcheck.py#L1954"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.gradcheck.gradcheck" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.gradcheck.</span></span><span class="sig-name descname"><span class="pre">gradcheck</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raise_exception</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nondet_tol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_undefined_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_grad_dtypes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_batched_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_batched_forward_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_forward_ad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_backward_ad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fast_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">masked</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/gradcheck.py#L1954"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.gradcheck.gradcheck" title="Permalink to this definition">#</a></dt>
 <dd><p>Check gradients computed via small finite differences against analytical
 gradients wrt tensors in <code class="xref py py-attr docutils literal notranslate"><span class="pre">inputs</span></code> that are of floating point or complex type
 and with <code class="docutils literal notranslate"><span class="pre">requires_grad=True</span></code>.</p>
diff --git a/2.9/generated/torch.autograd.gradcheck.gradgradcheck.html b/2.9/generated/torch.autograd.gradcheck.gradgradcheck.html
index a2b7c4f16cf..1e01bfa6608 100644
--- a/2.9/generated/torch.autograd.gradcheck.gradgradcheck.html
+++ b/2.9/generated/torch.autograd.gradcheck.gradgradcheck.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.gradcheck.gradgradcheck<a class="headerlink" href="#torch-autograd-gradcheck-gradgradcheck" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.gradcheck.gradgradcheck">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.gradcheck.</span></span><span class="sig-name descname"><span class="pre">gradgradcheck</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_outputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gen_non_contig_grad_outputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raise_exception</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nondet_tol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_undefined_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_grad_dtypes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_batched_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_fwd_over_rev</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_rev_over_rev</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fast_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">masked</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/gradcheck.py#L2119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.gradcheck.gradgradcheck" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.gradcheck.</span></span><span class="sig-name descname"><span class="pre">gradgradcheck</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_outputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gen_non_contig_grad_outputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raise_exception</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nondet_tol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_undefined_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_grad_dtypes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_batched_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_fwd_over_rev</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_rev_over_rev</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fast_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">masked</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/gradcheck.py#L2119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.gradcheck.gradgradcheck" title="Permalink to this definition">#</a></dt>
 <dd><p>Check gradients of gradients computed via small finite differences
 against analytical gradients wrt tensors in <code class="xref py py-attr docutils literal notranslate"><span class="pre">inputs</span></code> and
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">grad_outputs</span></code> that are of floating point or complex type and with
diff --git a/2.9/generated/torch.autograd.graph.Node.metadata.html b/2.9/generated/torch.autograd.graph.Node.metadata.html
index ddf7e6b444c..111fe5aac48 100644
--- a/2.9/generated/torch.autograd.graph.Node.metadata.html
+++ b/2.9/generated/torch.autograd.graph.Node.metadata.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.graph.Node.metadata<a class="headerlink" href="#torch-autograd-graph-node-metadata" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.graph.Node.metadata">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Node.</span></span><span class="sig-name descname"><span class="pre">metadata</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.Node.metadata" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Node.</span></span><span class="sig-name descname"><span class="pre">metadata</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.Node.metadata" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the metadata.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.autograd.graph.Node.name.html b/2.9/generated/torch.autograd.graph.Node.name.html
index 0d64b390586..f82f4565334 100644
--- a/2.9/generated/torch.autograd.graph.Node.name.html
+++ b/2.9/generated/torch.autograd.graph.Node.name.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.graph.Node.name<a class="headerlink" href="#torch-autograd-graph-node-name" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.graph.Node.name">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Node.</span></span><span class="sig-name descname"><span class="pre">name</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.Node.name" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Node.</span></span><span class="sig-name descname"><span class="pre">name</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.Node.name" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the name.</p>
 <p>Example:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">torch</span>
diff --git a/2.9/generated/torch.autograd.graph.Node.register_hook.html b/2.9/generated/torch.autograd.graph.Node.register_hook.html
index 0d02a9fa1ef..26e8ee75fbc 100644
--- a/2.9/generated/torch.autograd.graph.Node.register_hook.html
+++ b/2.9/generated/torch.autograd.graph.Node.register_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.graph.Node.register_hook<a class="headerlink" href="#torch-autograd-graph-node-register-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.graph.Node.register_hook">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Node.</span></span><span class="sig-name descname"><span class="pre">register_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.Node.register_hook" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Node.</span></span><span class="sig-name descname"><span class="pre">register_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.Node.register_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook.</p>
 <p>The hook will be called every time a gradient with respect to the
 Node is computed. The hook should have the following signature:</p>
diff --git a/2.9/generated/torch.autograd.graph.Node.register_prehook.html b/2.9/generated/torch.autograd.graph.Node.register_prehook.html
index 4ba05e47c26..1f927e430ea 100644
--- a/2.9/generated/torch.autograd.graph.Node.register_prehook.html
+++ b/2.9/generated/torch.autograd.graph.Node.register_prehook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.graph.Node.register_prehook<a class="headerlink" href="#torch-autograd-graph-node-register-prehook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.graph.Node.register_prehook">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Node.</span></span><span class="sig-name descname"><span class="pre">register_prehook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.Node.register_prehook" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">Node.</span></span><span class="sig-name descname"><span class="pre">register_prehook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.Node.register_prehook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward pre-hook.</p>
 <p>The hook will be called every time a gradient with respect to the
 Node is computed. The hook should have the following signature:</p>
diff --git a/2.9/generated/torch.autograd.graph.increment_version.html b/2.9/generated/torch.autograd.graph.increment_version.html
index bff7b683059..9a641bf25a3 100644
--- a/2.9/generated/torch.autograd.graph.increment_version.html
+++ b/2.9/generated/torch.autograd.graph.increment_version.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.graph.increment_version<a class="headerlink" href="#torch-autograd-graph-increment-version" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.graph.increment_version">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">increment_version</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/graph.py#L229"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.increment_version" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.graph.</span></span><span class="sig-name descname"><span class="pre">increment_version</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/graph.py#L229"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.graph.increment_version" title="Permalink to this definition">#</a></dt>
 <dd><p>Update autograd metadata tracking whether the given Tensor was modified in place.</p>
 <p>This is to enable more accurate error checking within the autograd engine.
 It is already done automatically by PyTorch functions and within custom Function
diff --git a/2.9/generated/torch.autograd.profiler.EnforceUnique.html b/2.9/generated/torch.autograd.profiler.EnforceUnique.html
index 48e759c3c6b..0f5d795c6e3 100644
--- a/2.9/generated/torch.autograd.profiler.EnforceUnique.html
+++ b/2.9/generated/torch.autograd.profiler.EnforceUnique.html
@@ -4404,11 +4404,11 @@
 <h1>EnforceUnique<a class="headerlink" href="#enforceunique" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler.EnforceUnique">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">EnforceUnique</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1051"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.EnforceUnique" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">EnforceUnique</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1051"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.EnforceUnique" title="Permalink to this definition">#</a></dt>
 <dd><p>Raises an error if a key is seen more than once.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler.EnforceUnique.see">
-<span class="sig-name descname"><span class="pre">see</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1057"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.EnforceUnique.see" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">see</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1057"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.EnforceUnique.see" title="Permalink to this definition">#</a></dt>
 <dd><p>Observe a key and raise an error if it is seen multiple times.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.autograd.profiler.KinetoStepTracker.html b/2.9/generated/torch.autograd.profiler.KinetoStepTracker.html
index 8d11daba80c..99439474e2d 100644
--- a/2.9/generated/torch.autograd.profiler.KinetoStepTracker.html
+++ b/2.9/generated/torch.autograd.profiler.KinetoStepTracker.html
@@ -4404,7 +4404,7 @@
 <h1>KinetoStepTracker<a class="headerlink" href="#kinetosteptracker" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler.KinetoStepTracker">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">KinetoStepTracker</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1133"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">KinetoStepTracker</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1133"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker" title="Permalink to this definition">#</a></dt>
 <dd><p>Provides an abstraction for incrementing the step count globally.</p>
 <p>Previously, we only had one place to mark that a step() has occurred
 in the program via pytorch profiler step(). We will now add step hooks
@@ -4439,7 +4439,7 @@ <h1>KinetoStepTracker<a class="headerlink" href="#kinetosteptracker" title="Perm
 for now. The result could be incorrect increments of the step count.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler.KinetoStepTracker.current_step">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">current_step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker.current_step" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">current_step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker.current_step" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the latest step for any requester</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4450,7 +4450,7 @@ <h1>KinetoStepTracker<a class="headerlink" href="#kinetosteptracker" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler.KinetoStepTracker.erase_step_count">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">erase_step_count</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requester</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker.erase_step_count" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">erase_step_count</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requester</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker.erase_step_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove a given requester.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4461,7 +4461,7 @@ <h1>KinetoStepTracker<a class="headerlink" href="#kinetosteptracker" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler.KinetoStepTracker.increment_step">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">increment_step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requester</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1192"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker.increment_step" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">increment_step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requester</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1192"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker.increment_step" title="Permalink to this definition">#</a></dt>
 <dd><p>Increments the step count for the requester.</p>
 <p>Additionally if the max over all step counts has incremented then
 trigger the _kineto_step() returns global step count</p>
@@ -4474,7 +4474,7 @@ <h1>KinetoStepTracker<a class="headerlink" href="#kinetosteptracker" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler.KinetoStepTracker.init_step_count">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">init_step_count</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requester</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1178"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker.init_step_count" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">init_step_count</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requester</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1178"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.KinetoStepTracker.init_step_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize for a given requester.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.autograd.profiler.load_nvprof.html b/2.9/generated/torch.autograd.profiler.load_nvprof.html
index 8580401a819..c863e57b578 100644
--- a/2.9/generated/torch.autograd.profiler.load_nvprof.html
+++ b/2.9/generated/torch.autograd.profiler.load_nvprof.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.profiler.load_nvprof<a class="headerlink" href="#torch-autograd-profiler-load-nvprof" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.profiler.load_nvprof">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">load_nvprof</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1042"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.load_nvprof" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">load_nvprof</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1042"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.load_nvprof" title="Permalink to this definition">#</a></dt>
 <dd><p>Open an nvprof trace file and parses autograd annotations.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.autograd.profiler.parse_nvprof_trace.html b/2.9/generated/torch.autograd.profiler.parse_nvprof_trace.html
index e68a4a2aab0..06a71b4a5f3 100644
--- a/2.9/generated/torch.autograd.profiler.parse_nvprof_trace.html
+++ b/2.9/generated/torch.autograd.profiler.parse_nvprof_trace.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.profiler.parse_nvprof_trace<a class="headerlink" href="#torch-autograd-profiler-parse-nvprof-trace" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.autograd.profiler.parse_nvprof_trace">
-<span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">parse_nvprof_trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L1066"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.parse_nvprof_trace" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">parse_nvprof_trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L1066"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.parse_nvprof_trace" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
diff --git a/2.9/generated/torch.autograd.profiler.profile.export_chrome_trace.html b/2.9/generated/torch.autograd.profiler.profile.export_chrome_trace.html
index d082d479fc0..aa70f628ff1 100644
--- a/2.9/generated/torch.autograd.profiler.profile.export_chrome_trace.html
+++ b/2.9/generated/torch.autograd.profiler.profile.export_chrome_trace.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.profiler.profile.export_chrome_trace<a class="headerlink" href="#torch-autograd-profiler-profile-export-chrome-trace" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler.profile.export_chrome_trace">
-<span class="sig-prename descclassname"><span class="pre">profile.</span></span><span class="sig-name descname"><span class="pre">export_chrome_trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L488"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.profile.export_chrome_trace" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">profile.</span></span><span class="sig-name descname"><span class="pre">export_chrome_trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L488"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.profile.export_chrome_trace" title="Permalink to this definition">#</a></dt>
 <dd><p>Export an EventList as a Chrome tracing tools file.</p>
 <p>The checkpoint can be later loaded and inspected under <code class="docutils literal notranslate"><span class="pre">chrome://tracing</span></code> URL.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.autograd.profiler.profile.key_averages.html b/2.9/generated/torch.autograd.profiler.profile.key_averages.html
index 5f1ed7f3194..eb9654a2b23 100644
--- a/2.9/generated/torch.autograd.profiler.profile.key_averages.html
+++ b/2.9/generated/torch.autograd.profiler.profile.key_averages.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.profiler.profile.key_averages<a class="headerlink" href="#torch-autograd-profiler-profile-key-averages" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler.profile.key_averages">
-<span class="sig-prename descclassname"><span class="pre">profile.</span></span><span class="sig-name descname"><span class="pre">key_averages</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group_by_input_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_by_stack_n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_by_overload_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L515"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.profile.key_averages" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">profile.</span></span><span class="sig-name descname"><span class="pre">key_averages</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group_by_input_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_by_stack_n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_by_overload_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L515"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.profile.key_averages" title="Permalink to this definition">#</a></dt>
 <dd><p>Averages all function events over their keys.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.autograd.profiler.profile.total_average.html b/2.9/generated/torch.autograd.profiler.profile.total_average.html
index 8d2b8125206..ed30718e80e 100644
--- a/2.9/generated/torch.autograd.profiler.profile.total_average.html
+++ b/2.9/generated/torch.autograd.profiler.profile.total_average.html
@@ -4404,7 +4404,7 @@
 <h1>torch.autograd.profiler.profile.total_average<a class="headerlink" href="#torch-autograd-profiler-profile-total-average" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler.profile.total_average">
-<span class="sig-prename descclassname"><span class="pre">profile.</span></span><span class="sig-name descname"><span class="pre">total_average</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L529"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.profile.total_average" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">profile.</span></span><span class="sig-name descname"><span class="pre">total_average</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L529"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.profile.total_average" title="Permalink to this definition">#</a></dt>
 <dd><p>Averages all events.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
diff --git a/2.9/generated/torch.autograd.profiler.record_function.html b/2.9/generated/torch.autograd.profiler.record_function.html
index e95b8a5facc..64f8b010aab 100644
--- a/2.9/generated/torch.autograd.profiler.record_function.html
+++ b/2.9/generated/torch.autograd.profiler.record_function.html
@@ -4404,7 +4404,7 @@
 <h1>record_function<a class="headerlink" href="#record-function" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler.record_function">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">record_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler.py#L733"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.record_function" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler.</span></span><span class="sig-name descname"><span class="pre">record_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler.py#L733"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler.record_function" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager/function decorator that adds a label to a code block/function when running autograd profiler.
 Label will only appear if CPU activity tracing is enabled.</p>
 <p>It is useful when tracing the code profile.</p>
diff --git a/2.9/generated/torch.autograd.profiler_util.Interval.html b/2.9/generated/torch.autograd.profiler_util.Interval.html
index a07857c8e9b..5e85ae4563a 100644
--- a/2.9/generated/torch.autograd.profiler_util.Interval.html
+++ b/2.9/generated/torch.autograd.profiler_util.Interval.html
@@ -4404,10 +4404,10 @@
 <h1>Interval<a class="headerlink" href="#interval" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler_util.Interval">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler_util.</span></span><span class="sig-name descname"><span class="pre">Interval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">start</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler_util.py#L448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.Interval" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler_util.</span></span><span class="sig-name descname"><span class="pre">Interval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">start</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler_util.py#L448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.Interval" title="Permalink to this definition">#</a></dt>
 <dd><dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler_util.Interval.elapsed_us">
-<span class="sig-name descname"><span class="pre">elapsed_us</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler_util.py#L453"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.Interval.elapsed_us" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">elapsed_us</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler_util.py#L453"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.Interval.elapsed_us" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the length of the interval</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.autograd.profiler_util.MemRecordsAcc.html b/2.9/generated/torch.autograd.profiler_util.MemRecordsAcc.html
index 018934aa00d..18b29941fb0 100644
--- a/2.9/generated/torch.autograd.profiler_util.MemRecordsAcc.html
+++ b/2.9/generated/torch.autograd.profiler_util.MemRecordsAcc.html
@@ -4404,11 +4404,11 @@
 <h1>MemRecordsAcc<a class="headerlink" href="#memrecordsacc" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler_util.MemRecordsAcc">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler_util.</span></span><span class="sig-name descname"><span class="pre">MemRecordsAcc</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mem_records</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler_util.py#L762"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.MemRecordsAcc" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler_util.</span></span><span class="sig-name descname"><span class="pre">MemRecordsAcc</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mem_records</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler_util.py#L762"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.MemRecordsAcc" title="Permalink to this definition">#</a></dt>
 <dd><p>Acceleration structure for accessing mem_records in interval.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler_util.MemRecordsAcc.in_interval">
-<span class="sig-name descname"><span class="pre">in_interval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">start_us</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end_us</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler_util.py#L773"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.MemRecordsAcc.in_interval" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">in_interval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">start_us</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end_us</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler_util.py#L773"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.MemRecordsAcc.in_interval" title="Permalink to this definition">#</a></dt>
 <dd><p>Return all records in the given interval
 To maintain backward compatibility, convert us to ns in function</p>
 </dd></dl>
diff --git a/2.9/generated/torch.autograd.profiler_util.StringTable.html b/2.9/generated/torch.autograd.profiler_util.StringTable.html
index a7839e80406..1893ca956a7 100644
--- a/2.9/generated/torch.autograd.profiler_util.StringTable.html
+++ b/2.9/generated/torch.autograd.profiler_util.StringTable.html
@@ -4404,7 +4404,7 @@
 <h1>StringTable<a class="headerlink" href="#stringtable" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.autograd.profiler_util.StringTable">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler_util.</span></span><span class="sig-name descname"><span class="pre">StringTable</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/profiler_util.py#L753"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.StringTable" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.autograd.profiler_util.</span></span><span class="sig-name descname"><span class="pre">StringTable</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/profiler_util.py#L753"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.autograd.profiler_util.StringTable" title="Permalink to this definition">#</a></dt>
 <dd><dl class="py method">
 <dt class="sig sig-object py" id="torch.autograd.profiler_util.StringTable.clear">
 <span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None.</span>&#160; <span class="pre">Remove</span> <span class="pre">all</span> <span class="pre">items</span> <span class="pre">from</span> <span class="pre">D.</span></span></span><a class="headerlink" href="#torch.autograd.profiler_util.StringTable.clear" title="Permalink to this definition">#</a></dt>
diff --git a/2.9/generated/torch.block_diag.html b/2.9/generated/torch.block_diag.html
index f89e44b7bbc..f3a238d7084 100644
--- a/2.9/generated/torch.block_diag.html
+++ b/2.9/generated/torch.block_diag.html
@@ -4404,7 +4404,7 @@
 <h1>torch.block_diag<a class="headerlink" href="#torch-block-diag" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.block_diag">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">block_diag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.block_diag" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">block_diag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.block_diag" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a block diagonal matrix from provided tensors.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.broadcast_shapes.html b/2.9/generated/torch.broadcast_shapes.html
index 27e97d580e9..ca8e8623674 100644
--- a/2.9/generated/torch.broadcast_shapes.html
+++ b/2.9/generated/torch.broadcast_shapes.html
@@ -4404,7 +4404,7 @@
 <h1>torch.broadcast_shapes<a class="headerlink" href="#torch-broadcast-shapes" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.broadcast_shapes">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">broadcast_shapes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">shapes</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../size.html#torch.Size" title="torch.Size"><span class="pre">Size</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.broadcast_shapes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">broadcast_shapes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">shapes</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../size.html#torch.Size" title="torch.Size"><span class="pre">Size</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.broadcast_shapes" title="Permalink to this definition">#</a></dt>
 <dd><p>Similar to <a class="reference internal" href="torch.broadcast_tensors.html#torch.broadcast_tensors" title="torch.broadcast_tensors"><code class="xref py py-func docutils literal notranslate"><span class="pre">broadcast_tensors()</span></code></a> but for shapes.</p>
 <p>This is equivalent to
 <code class="docutils literal notranslate"><span class="pre">torch.broadcast_tensors(*map(torch.empty,</span> <span class="pre">shapes))[0].shape</span></code>
diff --git a/2.9/generated/torch.broadcast_tensors.html b/2.9/generated/torch.broadcast_tensors.html
index 97f888b26d3..5d206f0e779 100644
--- a/2.9/generated/torch.broadcast_tensors.html
+++ b/2.9/generated/torch.broadcast_tensors.html
@@ -4404,7 +4404,7 @@
 <h1>torch.broadcast_tensors<a class="headerlink" href="#torch-broadcast-tensors" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.broadcast_tensors">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">broadcast_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">List</span> <span class="pre">of</span> <span class="pre">Tensors</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.broadcast_tensors" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">broadcast_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">List</span> <span class="pre">of</span> <span class="pre">Tensors</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.broadcast_tensors" title="Permalink to this definition">#</a></dt>
 <dd><p>Broadcasts the given tensors according to <a class="reference internal" href="../notes/broadcasting.html#broadcasting-semantics"><span class="std std-ref">Broadcasting semantics</span></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cartesian_prod.html b/2.9/generated/torch.cartesian_prod.html
index 77e38f1e751..d377de72827 100644
--- a/2.9/generated/torch.cartesian_prod.html
+++ b/2.9/generated/torch.cartesian_prod.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cartesian_prod<a class="headerlink" href="#torch-cartesian-prod" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cartesian_prod">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">cartesian_prod</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cartesian_prod" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">cartesian_prod</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cartesian_prod" title="Permalink to this definition">#</a></dt>
 <dd><p>Do cartesian product of the given sequence of tensors. The behavior is similar to
 python’s <cite>itertools.product</cite>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cdist.html b/2.9/generated/torch.cdist.html
index c8ca96575c0..898679d682f 100644
--- a/2.9/generated/torch.cdist.html
+++ b/2.9/generated/torch.cdist.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cdist<a class="headerlink" href="#torch-cdist" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cdist">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">cdist</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'use_mm_for_euclid_dist_if_necessary'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cdist" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">cdist</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'use_mm_for_euclid_dist_if_necessary'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cdist" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes batched the p-norm distance between each pair of the two collections of row vectors.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.chain_matmul.html b/2.9/generated/torch.chain_matmul.html
index ff1ee470f39..5e07f73778b 100644
--- a/2.9/generated/torch.chain_matmul.html
+++ b/2.9/generated/torch.chain_matmul.html
@@ -4404,7 +4404,7 @@
 <h1>torch.chain_matmul<a class="headerlink" href="#torch-chain-matmul" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.chain_matmul">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">chain_matmul</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">matrices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1981"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.chain_matmul" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">chain_matmul</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">matrices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1981"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.chain_matmul" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the matrix product of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>N</mi></mrow><annotation encoding="application/x-tex">N</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span></span></span></span></span> 2-D tensors. This product is efficiently computed
 using the matrix chain order algorithm which selects the order in which incurs the lowest cost in terms
 of arithmetic operations (<a class="reference external" href="https://mitpress.mit.edu/books/introduction-algorithms-third-edition">[CLRS]</a>). Note that since this is a function to compute the product, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>N</mi></mrow><annotation encoding="application/x-tex">N</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span></span></span></span></span>
diff --git a/2.9/generated/torch.compile.html b/2.9/generated/torch.compile.html
index 6af5ccd4c74..c01effb75c9 100644
--- a/2.9/generated/torch.compile.html
+++ b/2.9/generated/torch.compile.html
@@ -4404,7 +4404,7 @@
 <h1>torch.compile<a class="headerlink" href="#torch-compile" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compile">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="pre">_InputT</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">_RetT</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fullgraph</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'inductor'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">disable</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="pre">_InputT</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">_RetT</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L2478"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compile" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="pre">_InputT</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">_RetT</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fullgraph</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'inductor'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">disable</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="pre">_InputT</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">_RetT</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L2478"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compile" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fullgraph</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">'inductor'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">options</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">disable</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="pre">_InputT</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">_RetT</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="pre">_InputT</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">_RetT</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></span></dt>
 <dd><p>Optimizes given model/function using TorchDynamo and specified backend.
diff --git a/2.9/generated/torch.compiled_with_cxx11_abi.html b/2.9/generated/torch.compiled_with_cxx11_abi.html
index daaa5f353d6..dc17c8f4bdf 100644
--- a/2.9/generated/torch.compiled_with_cxx11_abi.html
+++ b/2.9/generated/torch.compiled_with_cxx11_abi.html
@@ -4404,7 +4404,7 @@
 <h1>torch.compiled_with_cxx11_abi<a class="headerlink" href="#torch-compiled-with-cxx11-abi" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiled_with_cxx11_abi">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">compiled_with_cxx11_abi</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L2259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiled_with_cxx11_abi" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">compiled_with_cxx11_abi</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L2259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiled_with_cxx11_abi" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether PyTorch was built with _GLIBCXX_USE_CXX11_ABI=1</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.compiler.allow_in_graph.html b/2.9/generated/torch.compiler.allow_in_graph.html
index 1f52b599197..84b1a10d8a8 100644
--- a/2.9/generated/torch.compiler.allow_in_graph.html
+++ b/2.9/generated/torch.compiler.allow_in_graph.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.allow_in_graph<a class="headerlink" href="#torch-compiler-allow-in-graph" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.allow_in_graph">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">allow_in_graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L66"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.allow_in_graph" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">allow_in_graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L66"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.allow_in_graph" title="Permalink to this definition">#</a></dt>
 <dd><p>Tells the compiler frontend (Dynamo) to skip symbolic introspection of the function
 and instead directly write it to the graph when encountered.</p>
 <p>If you are using <a class="reference internal" href="torch.compile.html#torch.compile" title="torch.compile"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.compile()</span></code></a> (with backend=”inductor” (the default)), or
diff --git a/2.9/generated/torch.compiler.assume_constant_result.html b/2.9/generated/torch.compiler.assume_constant_result.html
index 19cea81fc59..1159dbcef6f 100644
--- a/2.9/generated/torch.compiler.assume_constant_result.html
+++ b/2.9/generated/torch.compiler.assume_constant_result.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.assume_constant_result<a class="headerlink" href="#torch-compiler-assume-constant-result" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.assume_constant_result">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">assume_constant_result</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.assume_constant_result" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">assume_constant_result</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.assume_constant_result" title="Permalink to this definition">#</a></dt>
 <dd><p>This function is used to mark a function <cite>fn</cite> as having a constant result.
 This allows the compiler to optimize away your function.
 Returns The same function <cite>fn</cite></p>
diff --git a/2.9/generated/torch.compiler.compile.html b/2.9/generated/torch.compiler.compile.html
index 5d89b59d5e4..f27ea4063e0 100644
--- a/2.9/generated/torch.compiler.compile.html
+++ b/2.9/generated/torch.compiler.compile.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.compile<a class="headerlink" href="#torch-compiler-compile" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.compile">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.compile" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.compile" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.compile.html#torch.compile" title="torch.compile"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.compile()</span></code></a> for details on the arguments for this function.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.compiler.cudagraph_mark_step_begin.html b/2.9/generated/torch.compiler.cudagraph_mark_step_begin.html
index 753a25701e0..5c3dda95ae5 100644
--- a/2.9/generated/torch.compiler.cudagraph_mark_step_begin.html
+++ b/2.9/generated/torch.compiler.cudagraph_mark_step_begin.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.cudagraph_mark_step_begin<a class="headerlink" href="#torch-compiler-cudagraph-mark-step-begin" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.cudagraph_mark_step_begin">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">cudagraph_mark_step_begin</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.cudagraph_mark_step_begin" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">cudagraph_mark_step_begin</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.cudagraph_mark_step_begin" title="Permalink to this definition">#</a></dt>
 <dd><p>Indicates that a new iteration of inference or training is about to begin.</p>
 <p>CUDA Graphs will free tensors of a prior iteration. A new iteration is started on each invocation of
 torch.compile, so long as there is not a pending backward that has not been called.</p>
diff --git a/2.9/generated/torch.compiler.disable.html b/2.9/generated/torch.compiler.disable.html
index 7116f596369..ff8e3cf7d52 100644
--- a/2.9/generated/torch.compiler.disable.html
+++ b/2.9/generated/torch.compiler.disable.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.disable<a class="headerlink" href="#torch-compiler-disable" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.disable">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">disable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recursive</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reason</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L243"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.disable" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">disable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recursive</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reason</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L243"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.disable" title="Permalink to this definition">#</a></dt>
 <dd><p>This function provides a decorator to disable compilation on a function.
 It also provides the option of recursively disabling called functions.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.compiler.is_compiling.html b/2.9/generated/torch.compiler.is_compiling.html
index 3838e079a74..ed07f7f8dc9 100644
--- a/2.9/generated/torch.compiler.is_compiling.html
+++ b/2.9/generated/torch.compiler.is_compiling.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.is_compiling<a class="headerlink" href="#torch-compiler-is-compiling" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.is_compiling">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">is_compiling</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.is_compiling" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">is_compiling</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.is_compiling" title="Permalink to this definition">#</a></dt>
 <dd><p>Indicates whether a graph is executed/traced as part of torch.compile() or torch.export().</p>
 <dl class="simple">
 <dt>Note that there are 2 other related flags that should deprecated eventually:</dt><dd><ul class="simple">
diff --git a/2.9/generated/torch.compiler.is_dynamo_compiling.html b/2.9/generated/torch.compiler.is_dynamo_compiling.html
index c212616b0c6..07a1baeea84 100644
--- a/2.9/generated/torch.compiler.is_dynamo_compiling.html
+++ b/2.9/generated/torch.compiler.is_dynamo_compiling.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.is_dynamo_compiling<a class="headerlink" href="#torch-compiler-is-dynamo-compiling" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.is_dynamo_compiling">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">is_dynamo_compiling</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L458"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.is_dynamo_compiling" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">is_dynamo_compiling</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L458"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.is_dynamo_compiling" title="Permalink to this definition">#</a></dt>
 <dd><p>Indicates whether a graph is traced via TorchDynamo.</p>
 <p>It’s stricter than is_compiling() flag, as it would only be set to True when
 TorchDynamo is used.</p>
diff --git a/2.9/generated/torch.compiler.is_exporting.html b/2.9/generated/torch.compiler.is_exporting.html
index 70eab6d4df0..4b93ea5f43e 100644
--- a/2.9/generated/torch.compiler.is_exporting.html
+++ b/2.9/generated/torch.compiler.is_exporting.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.is_exporting<a class="headerlink" href="#torch-compiler-is-exporting" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.is_exporting">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">is_exporting</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L476"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.is_exporting" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">is_exporting</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L476"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.is_exporting" title="Permalink to this definition">#</a></dt>
 <dd><p>Indicated whether we’re under exporting.</p>
 <p>It’s stricter than is_compiling() flag, as it would only be set to True when
 torch.export is used.</p>
diff --git a/2.9/generated/torch.compiler.keep_tensor_guards_unsafe.html b/2.9/generated/torch.compiler.keep_tensor_guards_unsafe.html
index 62be1cc2e88..76bf06bce42 100644
--- a/2.9/generated/torch.compiler.keep_tensor_guards_unsafe.html
+++ b/2.9/generated/torch.compiler.keep_tensor_guards_unsafe.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.keep_tensor_guards_unsafe<a class="headerlink" href="#torch-compiler-keep-tensor-guards-unsafe" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.keep_tensor_guards_unsafe">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">keep_tensor_guards_unsafe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">guard_entries</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L571"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.keep_tensor_guards_unsafe" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">keep_tensor_guards_unsafe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">guard_entries</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L571"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.keep_tensor_guards_unsafe" title="Permalink to this definition">#</a></dt>
 <dd><p>A common function to keep tensor guards on all tensors. This is unsafe to
 use by default. But if you don’t expect any changes in the model code, you
 can just keep the tensor guards.</p>
diff --git a/2.9/generated/torch.compiler.list_backends.html b/2.9/generated/torch.compiler.list_backends.html
index 3eb93b3d84c..a1850365d47 100644
--- a/2.9/generated/torch.compiler.list_backends.html
+++ b/2.9/generated/torch.compiler.list_backends.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.list_backends<a class="headerlink" href="#torch-compiler-list-backends" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.list_backends">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">list_backends</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">exclude_tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">('debug',</span> <span class="pre">'experimental')</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.list_backends" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">list_backends</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">exclude_tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">('debug',</span> <span class="pre">'experimental')</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.list_backends" title="Permalink to this definition">#</a></dt>
 <dd><p>Return valid strings that can be passed to <cite>torch.compile(…, backend=”name”)</cite>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.compiler.nested_compile_region.html b/2.9/generated/torch.compiler.nested_compile_region.html
index a0d94108a36..9c3445a3bd7 100644
--- a/2.9/generated/torch.compiler.nested_compile_region.html
+++ b/2.9/generated/torch.compiler.nested_compile_region.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.nested_compile_region<a class="headerlink" href="#torch-compiler-nested-compile-region" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.nested_compile_region">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">nested_compile_region</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L613"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.nested_compile_region" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">nested_compile_region</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L613"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.nested_compile_region" title="Permalink to this definition">#</a></dt>
 <dd><p>Tells <strong>``torch.compile``</strong> that the marked set of operations forms a nested
 compile region (which is often repeated in the full model) whose code can be
 compiled once and safely reused.  <code class="docutils literal notranslate"><span class="pre">nested_compile_region</span></code> can also be used
diff --git a/2.9/generated/torch.compiler.reset.html b/2.9/generated/torch.compiler.reset.html
index 11b6dbd74f8..18b3c3d5cbb 100644
--- a/2.9/generated/torch.compiler.reset.html
+++ b/2.9/generated/torch.compiler.reset.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.reset<a class="headerlink" href="#torch-compiler-reset" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.reset">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L55"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.reset" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L55"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.reset" title="Permalink to this definition">#</a></dt>
 <dd><p>This function clears all compilation caches and restores the system to its initial state.
 It is recommended to call this function, especially after using operations like <cite>torch.compile(…)</cite>
 to ensure a clean state before another unrelated compilation</p>
diff --git a/2.9/generated/torch.compiler.set_enable_guard_collectives.html b/2.9/generated/torch.compiler.set_enable_guard_collectives.html
index 28aded32e80..3ff69fde7fc 100644
--- a/2.9/generated/torch.compiler.set_enable_guard_collectives.html
+++ b/2.9/generated/torch.compiler.set_enable_guard_collectives.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.set_enable_guard_collectives<a class="headerlink" href="#torch-compiler-set-enable-guard-collectives" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.set_enable_guard_collectives">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">set_enable_guard_collectives</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L344"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.set_enable_guard_collectives" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">set_enable_guard_collectives</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L344"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.set_enable_guard_collectives" title="Permalink to this definition">#</a></dt>
 <dd><p>Enables use of collectives <em>during</em> guard evaluation to synchronize behavior
 across ranks.  This is expensive: we have to issue a collective every time
 we enter a compiled code region, even if no rank actually would need to
diff --git a/2.9/generated/torch.compiler.set_stance.html b/2.9/generated/torch.compiler.set_stance.html
index 57a84ee9ddc..663857c85cc 100644
--- a/2.9/generated/torch.compiler.set_stance.html
+++ b/2.9/generated/torch.compiler.set_stance.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.set_stance<a class="headerlink" href="#torch-compiler-set-stance" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.set_stance">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">set_stance</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'default'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_guard_eval_unsafe</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L258"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.set_stance" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">set_stance</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stance</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'default'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_guard_eval_unsafe</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L258"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.set_stance" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the current stance of the compiler.
 Can be used as a function, context manager, or decorator.
 Do not use this function inside a <cite>torch.compile</cite> region - an error will be raised otherwise.</p>
diff --git a/2.9/generated/torch.compiler.skip_guard_on_all_nn_modules_unsafe.html b/2.9/generated/torch.compiler.skip_guard_on_all_nn_modules_unsafe.html
index 694077ecd1c..e0ad2168a53 100644
--- a/2.9/generated/torch.compiler.skip_guard_on_all_nn_modules_unsafe.html
+++ b/2.9/generated/torch.compiler.skip_guard_on_all_nn_modules_unsafe.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.skip_guard_on_all_nn_modules_unsafe<a class="headerlink" href="#torch-compiler-skip-guard-on-all-nn-modules-unsafe" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.skip_guard_on_all_nn_modules_unsafe">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">skip_guard_on_all_nn_modules_unsafe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">guard_entries</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L549"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.skip_guard_on_all_nn_modules_unsafe" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">skip_guard_on_all_nn_modules_unsafe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">guard_entries</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L549"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.skip_guard_on_all_nn_modules_unsafe" title="Permalink to this definition">#</a></dt>
 <dd><p>A common function to skip guards on all nn modules, both user defined as
 well inbuilt nn modules (like torch.nn.Linear). This is unsafe to use by
 default. But for majority of torch.compile users, the model code does not
diff --git a/2.9/generated/torch.compiler.skip_guard_on_globals_unsafe.html b/2.9/generated/torch.compiler.skip_guard_on_globals_unsafe.html
index 26560f0ce54..dd011dc646c 100644
--- a/2.9/generated/torch.compiler.skip_guard_on_globals_unsafe.html
+++ b/2.9/generated/torch.compiler.skip_guard_on_globals_unsafe.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.skip_guard_on_globals_unsafe<a class="headerlink" href="#torch-compiler-skip-guard-on-globals-unsafe" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.skip_guard_on_globals_unsafe">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">skip_guard_on_globals_unsafe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">guard_entries</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L598"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.skip_guard_on_globals_unsafe" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">skip_guard_on_globals_unsafe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">guard_entries</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L598"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.skip_guard_on_globals_unsafe" title="Permalink to this definition">#</a></dt>
 <dd><p>A common function to skip guards on all globals. This is unsafe to use by
 default. But if you don’t expect any changes in the globals, you can just
 keep the tensor guards.</p>
diff --git a/2.9/generated/torch.compiler.skip_guard_on_inbuilt_nn_modules_unsafe.html b/2.9/generated/torch.compiler.skip_guard_on_inbuilt_nn_modules_unsafe.html
index a0c09eb291f..821dd59d357 100644
--- a/2.9/generated/torch.compiler.skip_guard_on_inbuilt_nn_modules_unsafe.html
+++ b/2.9/generated/torch.compiler.skip_guard_on_inbuilt_nn_modules_unsafe.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.skip_guard_on_inbuilt_nn_modules_unsafe<a class="headerlink" href="#torch-compiler-skip-guard-on-inbuilt-nn-modules-unsafe" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.skip_guard_on_inbuilt_nn_modules_unsafe">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">skip_guard_on_inbuilt_nn_modules_unsafe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">guard_entries</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.skip_guard_on_inbuilt_nn_modules_unsafe" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">skip_guard_on_inbuilt_nn_modules_unsafe</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">guard_entries</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.skip_guard_on_inbuilt_nn_modules_unsafe" title="Permalink to this definition">#</a></dt>
 <dd><p>A common function to skip guards on the inbuilt nn modules like
 torch.nn.Linear. This is unsafe to use by default. But for majority of
 torch.compile users, the model code does not modify the inbuilt nn module
diff --git a/2.9/generated/torch.compiler.substitute_in_graph.html b/2.9/generated/torch.compiler.substitute_in_graph.html
index 79a9ed9cd62..548677a9e16 100644
--- a/2.9/generated/torch.compiler.substitute_in_graph.html
+++ b/2.9/generated/torch.compiler.substitute_in_graph.html
@@ -4415,7 +4415,7 @@
 <h1>torch.compiler.substitute_in_graph<a class="headerlink" href="#torch-compiler-substitute-in-graph" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.compiler.substitute_in_graph">
-<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">substitute_in_graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">original_fn</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">can_constant_fold_through</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_signature_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/compiler/__init__.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.substitute_in_graph" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.compiler.</span></span><span class="sig-name descname"><span class="pre">substitute_in_graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">original_fn</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">can_constant_fold_through</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_signature_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/compiler/__init__.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.compiler.substitute_in_graph" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a polyfill handler for a function, usually a C function from the C extension, to be
 used in place of the original function when inlining the original function in the graph.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.cond.html b/2.9/generated/torch.cond.html
index 1e4a352d9c9..6aad087c9bb 100644
--- a/2.9/generated/torch.cond.html
+++ b/2.9/generated/torch.cond.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cond<a class="headerlink" href="#torch-cond" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cond">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">cond</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pred</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">true_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">false_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">operands</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_higher_order_ops/cond.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cond" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">cond</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pred</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">true_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">false_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">operands</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_higher_order_ops/cond.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cond" title="Permalink to this definition">#</a></dt>
 <dd><p>Conditionally applies <cite>true_fn</cite> or <cite>false_fn</cite>.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.cpu.Stream.html b/2.9/generated/torch.cpu.Stream.html
index 6197b8d453e..4b66827ffcb 100644
--- a/2.9/generated/torch.cpu.Stream.html
+++ b/2.9/generated/torch.cpu.Stream.html
@@ -4404,7 +4404,7 @@
 <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cpu.Stream">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">Stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">priority</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.Stream" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">Stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">priority</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.Stream" title="Permalink to this definition">#</a></dt>
 <dd><p>N.B. This class only exists to facilitate device-agnostic code</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.cpu.StreamContext.html b/2.9/generated/torch.cpu.StreamContext.html
index bc52ac87e66..10580816fc0 100644
--- a/2.9/generated/torch.cpu.StreamContext.html
+++ b/2.9/generated/torch.cpu.StreamContext.html
@@ -4404,7 +4404,7 @@
 <h1>StreamContext<a class="headerlink" href="#streamcontext" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cpu.StreamContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">StreamContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.StreamContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">StreamContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.StreamContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that selects a given stream.</p>
 <p>N.B. This class only exists to facilitate device-agnostic code</p>
 </dd></dl>
diff --git a/2.9/generated/torch.cpu.current_device.html b/2.9/generated/torch.cpu.current_device.html
index 6108858aa35..038137d3613 100644
--- a/2.9/generated/torch.cpu.current_device.html
+++ b/2.9/generated/torch.cpu.current_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cpu.current_device<a class="headerlink" href="#torch-cpu-current-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cpu.current_device">
-<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">current_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.current_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">current_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.current_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns current device for cpu. Always ‘cpu’.</p>
 <p>N.B. This function only exists to facilitate device-agnostic code</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cpu.current_stream.html b/2.9/generated/torch.cpu.current_stream.html
index 5dbce412888..21750e23d6a 100644
--- a/2.9/generated/torch.cpu.current_stream.html
+++ b/2.9/generated/torch.cpu.current_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cpu.current_stream<a class="headerlink" href="#torch-cpu-current-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cpu.current_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.current_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.current_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the currently selected <a class="reference internal" href="torch.cpu.Stream.html#torch.cpu.Stream" title="torch.cpu.Stream"><code class="xref py py-class docutils literal notranslate"><span class="pre">Stream</span></code></a> for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cpu.device_count.html b/2.9/generated/torch.cpu.device_count.html
index 236b3475b1f..1d462a157d3 100644
--- a/2.9/generated/torch.cpu.device_count.html
+++ b/2.9/generated/torch.cpu.device_count.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cpu.device_count<a class="headerlink" href="#torch-cpu-device-count" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cpu.device_count">
-<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.device_count" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.device_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns number of CPU devices (not cores). Always 1.</p>
 <p>N.B. This function only exists to facilitate device-agnostic code</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cpu.is_available.html b/2.9/generated/torch.cpu.is_available.html
index e7a60a77860..2ee2d52c65b 100644
--- a/2.9/generated/torch.cpu.is_available.html
+++ b/2.9/generated/torch.cpu.is_available.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cpu.is_available<a class="headerlink" href="#torch-cpu-is-available" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cpu.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L67"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L67"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a bool indicating if CPU is currently available.</p>
 <p>N.B. This function only exists to facilitate device-agnostic code</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cpu.set_device.html b/2.9/generated/torch.cpu.set_device.html
index e0891f50f4e..c5bc867e832 100644
--- a/2.9/generated/torch.cpu.set_device.html
+++ b/2.9/generated/torch.cpu.set_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cpu.set_device<a class="headerlink" href="#torch-cpu-set-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cpu.set_device">
-<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">set_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L182"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.set_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">set_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L182"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.set_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the current device, in CPU we do nothing.</p>
 <p>N.B. This function only exists to facilitate device-agnostic code</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cpu.stream.html b/2.9/generated/torch.cpu.stream.html
index 840be504e8b..33fcb0d5678 100644
--- a/2.9/generated/torch.cpu.stream.html
+++ b/2.9/generated/torch.cpu.stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cpu.stream<a class="headerlink" href="#torch-cpu-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cpu.stream">
-<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around the Context-manager StreamContext that
 selects a given stream.</p>
 <p>N.B. This function only exists to facilitate device-agnostic code</p>
diff --git a/2.9/generated/torch.cpu.synchronize.html b/2.9/generated/torch.cpu.synchronize.html
index 8c53fc36fda..38fb26fa7da 100644
--- a/2.9/generated/torch.cpu.synchronize.html
+++ b/2.9/generated/torch.cpu.synchronize.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cpu.synchronize<a class="headerlink" href="#torch-cpu-synchronize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cpu.synchronize">
-<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cpu/__init__.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cpu.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cpu/__init__.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cpu.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Waits for all kernels in all streams on the CPU device to complete.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.CUDAGraph.html b/2.9/generated/torch.cuda.CUDAGraph.html
index 8df94e6028a..d713a70c42f 100644
--- a/2.9/generated/torch.cuda.CUDAGraph.html
+++ b/2.9/generated/torch.cuda.CUDAGraph.html
@@ -4404,7 +4404,7 @@
 <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">CUDAGraph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keep_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">CUDAGraph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keep_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around a CUDA graph.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4436,7 +4436,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.capture_begin">
-<span class="sig-name descname"><span class="pre">capture_begin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pool</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capture_error_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'global'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.capture_begin" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">capture_begin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pool</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capture_error_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'global'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.capture_begin" title="Permalink to this definition">#</a></dt>
 <dd><p>Begin capturing CUDA work on the current stream.</p>
 <p>Typically, you shouldn’t call <code class="docutils literal notranslate"><span class="pre">capture_begin</span></code> yourself.
 Use <a class="reference internal" href="torch.cuda.graph.html#torch.cuda.graph" title="torch.cuda.graph"><code class="xref py py-class docutils literal notranslate"><span class="pre">graph</span></code></a> or <a class="reference internal" href="torch.cuda.make_graphed_callables.html#torch.cuda.make_graphed_callables" title="torch.cuda.make_graphed_callables"><code class="xref py py-func docutils literal notranslate"><span class="pre">make_graphed_callables()</span></code></a>,
@@ -4459,7 +4459,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.capture_end">
-<span class="sig-name descname"><span class="pre">capture_end</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.capture_end" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">capture_end</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.capture_end" title="Permalink to this definition">#</a></dt>
 <dd><p>End CUDA graph capture on the current stream.</p>
 <p>After <code class="docutils literal notranslate"><span class="pre">capture_end</span></code>, <code class="docutils literal notranslate"><span class="pre">replay</span></code> may be called on this instance.</p>
 <p>Typically, you shouldn’t call <code class="docutils literal notranslate"><span class="pre">capture_end</span></code> yourself.
@@ -4471,7 +4471,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.debug_dump">
-<span class="sig-name descname"><span class="pre">debug_dump</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">debug_path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.debug_dump" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">debug_dump</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">debug_path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.debug_dump" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
 <dd class="field-odd"><p><strong>debug_path</strong> (<em>required</em>) – Path to dump the graph to.</p>
@@ -4483,7 +4483,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.enable_debug_mode">
-<span class="sig-name descname"><span class="pre">enable_debug_mode</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.enable_debug_mode" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">enable_debug_mode</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.enable_debug_mode" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable debugging mode for CUDAGraph.debug_dump.</p>
 <dl class="field-list simple">
 </dl>
@@ -4491,7 +4491,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.instantiate">
-<span class="sig-name descname"><span class="pre">instantiate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.instantiate" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">instantiate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.instantiate" title="Permalink to this definition">#</a></dt>
 <dd><p>Instantiate the CUDA graph. Will be called by
 <code class="docutils literal notranslate"><span class="pre">capture_end</span></code> if <code class="docutils literal notranslate"><span class="pre">keep_graph=False</span></code>, or by <code class="docutils literal notranslate"><span class="pre">replay</span></code> if
 <code class="docutils literal notranslate"><span class="pre">keep_graph=True</span></code> and <code class="docutils literal notranslate"><span class="pre">instantiate</span></code> has not already been
@@ -4503,7 +4503,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.pool">
-<span class="sig-name descname"><span class="pre">pool</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L147"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.pool" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pool</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L147"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.pool" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an opaque token representing the id of this graph’s memory pool.</p>
 <p>This id can optionally be passed to another graph’s <code class="docutils literal notranslate"><span class="pre">capture_begin</span></code>,
 which hints the other graph may share the same memory pool.</p>
@@ -4516,7 +4516,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.raw_cuda_graph">
-<span class="sig-name descname"><span class="pre">raw_cuda_graph</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.raw_cuda_graph" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">raw_cuda_graph</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.raw_cuda_graph" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the underlying cudaGraph_t. <code class="docutils literal notranslate"><span class="pre">keep_graph</span></code> must be True.</p>
 <p>See the following for APIs for how to manipulate this object: <a class="reference external" href="https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__GRAPH.html">Graph Managmement</a> and <a class="reference external" href="https://nvidia.github.io/cuda-python/cuda-bindings/latest/module/runtime.html#graph-management">cuda-python Graph Management bindings</a></p>
 <dl class="field-list simple">
@@ -4528,7 +4528,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.raw_cuda_graph_exec">
-<span class="sig-name descname"><span class="pre">raw_cuda_graph_exec</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.raw_cuda_graph_exec" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">raw_cuda_graph_exec</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.raw_cuda_graph_exec" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the underlying cudaGraphExec_t. <code class="docutils literal notranslate"><span class="pre">instantiate</span></code> must have been called if <code class="docutils literal notranslate"><span class="pre">keep_graph</span></code> is True, or <code class="docutils literal notranslate"><span class="pre">capture_end</span></code> must have been called if <code class="docutils literal notranslate"><span class="pre">keep_graph</span></code> is False. If you call <code class="docutils literal notranslate"><span class="pre">instantiate()</span></code> after <code class="docutils literal notranslate"><span class="pre">raw_cuda_graph_exec()</span></code>, the previously returned cudaGraphExec_t will be destroyed. It is your responsibility not to use this object after destruction.</p>
 <p>See the following for APIs for how to manipulate this object: <a class="reference external" href="https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__GRAPH__EXEC.html">Graph Execution</a> and <a class="reference external" href="https://nvidia.github.io/cuda-python/cuda-bindings/latest/module/runtime.html#graph-execution">cuda-python Graph Execution bindings</a></p>
 <dl class="field-list simple">
@@ -4540,7 +4540,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.replay">
-<span class="sig-name descname"><span class="pre">replay</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.replay" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">replay</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.replay" title="Permalink to this definition">#</a></dt>
 <dd><p>Replay the CUDA work captured by this graph.</p>
 <dl class="field-list simple">
 </dl>
@@ -4548,7 +4548,7 @@ <h1>CUDAGraph<a class="headerlink" href="#cudagraph" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.CUDAGraph.reset">
-<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.reset" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.CUDAGraph.reset" title="Permalink to this definition">#</a></dt>
 <dd><p>Delete the graph currently held by this instance.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.cuda.Event.html b/2.9/generated/torch.cuda.Event.html
index 77df04e9158..5ff037047c1 100644
--- a/2.9/generated/torch.cuda.Event.html
+++ b/2.9/generated/torch.cuda.Event.html
@@ -4404,7 +4404,7 @@
 <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.Event">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">Event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable_timing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">interprocess</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">external</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">Event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable_timing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">interprocess</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">external</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around a CUDA event.</p>
 <p>CUDA events are synchronization markers that can be used to monitor the
 device’s progress, to accurately measure timing, and to synchronize CUDA
@@ -4427,7 +4427,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Event.elapsed_time">
-<span class="sig-name descname"><span class="pre">elapsed_time</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">end_event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.elapsed_time" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">elapsed_time</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">end_event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.elapsed_time" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the time elapsed.</p>
 <p>Time reported in milliseconds after the event was recorded and
 before the end_event was recorded.</p>
@@ -4435,20 +4435,20 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Event.from_ipc_handle">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_ipc_handle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">handle</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L178"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.from_ipc_handle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_ipc_handle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">handle</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L178"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.from_ipc_handle" title="Permalink to this definition">#</a></dt>
 <dd><p>Reconstruct an event from an IPC handle on the given device.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Event.ipc_handle">
-<span class="sig-name descname"><span class="pre">ipc_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.ipc_handle" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">ipc_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L233"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.ipc_handle" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an IPC handle of this event.</p>
 <p>If not recorded yet, the event will use the current device.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Event.query">
-<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.query" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.query" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if all work currently captured by event has completed.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4460,7 +4460,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Event.record">
-<span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.record" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.record" title="Permalink to this definition">#</a></dt>
 <dd><p>Record the event in a given stream.</p>
 <p>Uses <code class="docutils literal notranslate"><span class="pre">torch.cuda.current_stream()</span></code> if no stream is specified. The
 stream’s device must match the event’s device.</p>
@@ -4468,7 +4468,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Event.synchronize">
-<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L222"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L222"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait for the event to complete.</p>
 <p>Waits until the completion of all work currently captured in this event.
 This prevents the CPU thread from proceeding until the event completes.</p>
@@ -4485,7 +4485,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Event.wait">
-<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L193"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.wait" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L193"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Event.wait" title="Permalink to this definition">#</a></dt>
 <dd><p>Make all future work submitted to the given stream wait for this event.</p>
 <p>Use <code class="docutils literal notranslate"><span class="pre">torch.cuda.current_stream()</span></code> if no stream is specified.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.cuda.ExternalStream.html b/2.9/generated/torch.cuda.ExternalStream.html
index f8e1c1a6409..b2faaef7d7e 100644
--- a/2.9/generated/torch.cuda.ExternalStream.html
+++ b/2.9/generated/torch.cuda.ExternalStream.html
@@ -4404,7 +4404,7 @@
 <h1>ExternalStream<a class="headerlink" href="#externalstream" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.ExternalStream">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">ExternalStream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream_ptr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">ExternalStream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream_ptr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around an externally allocated CUDA stream.</p>
 <p>This class is used to wrap streams allocated in other libraries in order
 to facilitate data exchange and multi-library interactions.</p>
@@ -4427,7 +4427,7 @@ <h1>ExternalStream<a class="headerlink" href="#externalstream" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.ExternalStream.query">
-<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.query" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.query" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if all the work submitted has been completed.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4441,7 +4441,7 @@ <h1>ExternalStream<a class="headerlink" href="#externalstream" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.ExternalStream.record_event">
-<span class="sig-name descname"><span class="pre">record_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.record_event" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">record_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.record_event" title="Permalink to this definition">#</a></dt>
 <dd><p>Record an event.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4456,7 +4456,7 @@ <h1>ExternalStream<a class="headerlink" href="#externalstream" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.ExternalStream.synchronize">
-<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait for all the kernels in this stream to complete.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4469,7 +4469,7 @@ <h1>ExternalStream<a class="headerlink" href="#externalstream" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.ExternalStream.wait_event">
-<span class="sig-name descname"><span class="pre">wait_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.wait_event" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.wait_event" title="Permalink to this definition">#</a></dt>
 <dd><p>Make all future work submitted to the stream wait for an event.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4487,7 +4487,7 @@ <h1>ExternalStream<a class="headerlink" href="#externalstream" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.ExternalStream.wait_stream">
-<span class="sig-name descname"><span class="pre">wait_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.wait_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ExternalStream.wait_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Synchronize with another stream.</p>
 <p>All future work submitted to this stream will wait until all kernels
 submitted to a given stream at the time of call complete.</p>
diff --git a/2.9/generated/torch.cuda.Stream.html b/2.9/generated/torch.cuda.Stream.html
index 04a565aeb03..f0daba40146 100644
--- a/2.9/generated/torch.cuda.Stream.html
+++ b/2.9/generated/torch.cuda.Stream.html
@@ -4404,7 +4404,7 @@
 <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.Stream">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">Stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">priority</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">Stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">priority</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around a CUDA stream.</p>
 <p>A CUDA stream is a linear sequence of execution that belongs to a specific
 device, independent from other streams. It supports with statement as a
@@ -4426,7 +4426,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Stream.query">
-<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.query" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.query" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if all the work submitted has been completed.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4440,7 +4440,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Stream.record_event">
-<span class="sig-name descname"><span class="pre">record_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.record_event" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">record_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.record_event" title="Permalink to this definition">#</a></dt>
 <dd><p>Record an event.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4455,7 +4455,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Stream.synchronize">
-<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait for all the kernels in this stream to complete.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4468,7 +4468,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Stream.wait_event">
-<span class="sig-name descname"><span class="pre">wait_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.wait_event" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.wait_event" title="Permalink to this definition">#</a></dt>
 <dd><p>Make all future work submitted to the stream wait for an event.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4486,7 +4486,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.Stream.wait_stream">
-<span class="sig-name descname"><span class="pre">wait_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/streams.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.wait_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/streams.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.Stream.wait_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Synchronize with another stream.</p>
 <p>All future work submitted to this stream will wait until all kernels
 submitted to a given stream at the time of call complete.</p>
diff --git a/2.9/generated/torch.cuda.StreamContext.html b/2.9/generated/torch.cuda.StreamContext.html
index f446e6522bf..a271027cefb 100644
--- a/2.9/generated/torch.cuda.StreamContext.html
+++ b/2.9/generated/torch.cuda.StreamContext.html
@@ -4404,7 +4404,7 @@
 <h1>StreamContext<a class="headerlink" href="#streamcontext" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.StreamContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">StreamContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.StreamContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">StreamContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.StreamContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that selects a given stream.</p>
 <p>All CUDA kernels queued within its context will be enqueued on a selected
 stream.</p>
diff --git a/2.9/generated/torch.cuda.can_device_access_peer.html b/2.9/generated/torch.cuda.can_device_access_peer.html
index d87904a2ae7..0eb44b9d05b 100644
--- a/2.9/generated/torch.cuda.can_device_access_peer.html
+++ b/2.9/generated/torch.cuda.can_device_access_peer.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.can_device_access_peer<a class="headerlink" href="#torch-cuda-can-device-access-peer" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.can_device_access_peer">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">can_device_access_peer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">peer_device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L621"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.can_device_access_peer" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">can_device_access_peer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">peer_device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L621"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.can_device_access_peer" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if peer access between two devices is possible.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.clock_rate.html b/2.9/generated/torch.cuda.clock_rate.html
index 2007a73607f..6f23c47a079 100644
--- a/2.9/generated/torch.cuda.clock_rate.html
+++ b/2.9/generated/torch.cuda.clock_rate.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.clock_rate<a class="headerlink" href="#torch-cuda-clock-rate" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.clock_rate">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">clock_rate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1406"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.clock_rate" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">clock_rate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1406"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.clock_rate" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the clock speed of the GPU SM in MHz (megahertz) over the past sample period as given by <cite>nvidia-smi</cite>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.comm.broadcast.html b/2.9/generated/torch.cuda.comm.broadcast.html
index a127ca11611..9f81ba2199b 100644
--- a/2.9/generated/torch.cuda.comm.broadcast.html
+++ b/2.9/generated/torch.cuda.comm.broadcast.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.comm.broadcast<a class="headerlink" href="#torch-cuda-comm-broadcast" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.comm.broadcast">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">broadcast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/comm.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.broadcast" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">broadcast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/comm.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.broadcast" title="Permalink to this definition">#</a></dt>
 <dd><p>Broadcasts a tensor to specified GPU devices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.comm.broadcast_coalesced.html b/2.9/generated/torch.cuda.comm.broadcast_coalesced.html
index 8ec76968fbb..7b6e7273f28 100644
--- a/2.9/generated/torch.cuda.comm.broadcast_coalesced.html
+++ b/2.9/generated/torch.cuda.comm.broadcast_coalesced.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.comm.broadcast_coalesced<a class="headerlink" href="#torch-cuda-comm-broadcast-coalesced" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.comm.broadcast_coalesced">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">broadcast_coalesced</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffer_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10485760</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/comm.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.broadcast_coalesced" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">broadcast_coalesced</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffer_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10485760</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/comm.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.broadcast_coalesced" title="Permalink to this definition">#</a></dt>
 <dd><p>Broadcast a sequence of tensors to the specified GPUs.</p>
 <p>Small tensors are first coalesced into a buffer to reduce the number of synchronizations.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cuda.comm.gather.html b/2.9/generated/torch.cuda.comm.gather.html
index 18f1a45d3ba..d82fd58be02 100644
--- a/2.9/generated/torch.cuda.comm.gather.html
+++ b/2.9/generated/torch.cuda.comm.gather.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.comm.gather<a class="headerlink" href="#torch-cuda-comm-gather" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.comm.gather">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">gather</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/comm.py#L217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.gather" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">gather</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/comm.py#L217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.gather" title="Permalink to this definition">#</a></dt>
 <dd><p>Gathers tensors from multiple GPU devices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.comm.reduce_add.html b/2.9/generated/torch.cuda.comm.reduce_add.html
index 3d7d6b1e06d..70dadf3a0db 100644
--- a/2.9/generated/torch.cuda.comm.reduce_add.html
+++ b/2.9/generated/torch.cuda.comm.reduce_add.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.comm.reduce_add<a class="headerlink" href="#torch-cuda-comm-reduce-add" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.comm.reduce_add">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">reduce_add</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/comm.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.reduce_add" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">reduce_add</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/comm.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.reduce_add" title="Permalink to this definition">#</a></dt>
 <dd><p>Sum tensors from multiple GPUs.</p>
 <p>All inputs should have matching shapes, dtype, and layout. The output tensor
 will be of the same shape, dtype, and layout.</p>
diff --git a/2.9/generated/torch.cuda.comm.reduce_add_coalesced.html b/2.9/generated/torch.cuda.comm.reduce_add_coalesced.html
index b0a29eee512..4e070a6b642 100644
--- a/2.9/generated/torch.cuda.comm.reduce_add_coalesced.html
+++ b/2.9/generated/torch.cuda.comm.reduce_add_coalesced.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.comm.reduce_add_coalesced<a class="headerlink" href="#torch-cuda-comm-reduce-add-coalesced" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.comm.reduce_add_coalesced">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">reduce_add_coalesced</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffer_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10485760</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/comm.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.reduce_add_coalesced" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">reduce_add_coalesced</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">buffer_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10485760</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/comm.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.reduce_add_coalesced" title="Permalink to this definition">#</a></dt>
 <dd><p>Sum tensors from multiple GPUs.</p>
 <p>Small tensors are first coalesced into a buffer to reduce the number
 of synchronizations.</p>
diff --git a/2.9/generated/torch.cuda.comm.scatter.html b/2.9/generated/torch.cuda.comm.scatter.html
index e73fbe91202..3c36bbb0cde 100644
--- a/2.9/generated/torch.cuda.comm.scatter.html
+++ b/2.9/generated/torch.cuda.comm.scatter.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.comm.scatter<a class="headerlink" href="#torch-cuda-comm-scatter" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.comm.scatter">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">scatter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">streams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/comm.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.scatter" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.comm.</span></span><span class="sig-name descname"><span class="pre">scatter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">streams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/comm.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.comm.scatter" title="Permalink to this definition">#</a></dt>
 <dd><p>Scatters tensor across multiple GPUs.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.cudart.html b/2.9/generated/torch.cuda.cudart.html
index bff456e2789..2a6ff2e998c 100644
--- a/2.9/generated/torch.cuda.cudart.html
+++ b/2.9/generated/torch.cuda.cudart.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.cudart<a class="headerlink" href="#torch-cuda-cudart" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.cudart">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">cudart</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L433"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.cudart" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">cudart</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L433"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.cudart" title="Permalink to this definition">#</a></dt>
 <dd><p>Retrieves the CUDA runtime API module.</p>
 <p>This function initializes the CUDA runtime environment if it is not already
 initialized and returns the CUDA runtime API module (_cudart). The CUDA
diff --git a/2.9/generated/torch.cuda.current_blas_handle.html b/2.9/generated/torch.cuda.current_blas_handle.html
index ee5f8552390..b7c5cac8b5c 100644
--- a/2.9/generated/torch.cuda.current_blas_handle.html
+++ b/2.9/generated/torch.cuda.current_blas_handle.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.current_blas_handle<a class="headerlink" href="#torch-cuda-current-blas-handle" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.current_blas_handle">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">current_blas_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.current_blas_handle" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">current_blas_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.current_blas_handle" title="Permalink to this definition">#</a></dt>
 <dd><p>Return cublasHandle_t pointer to current cuBLAS handle</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.cuda.current_device.html b/2.9/generated/torch.cuda.current_device.html
index fb7ff8a4f1f..f7032996f1d 100644
--- a/2.9/generated/torch.cuda.current_device.html
+++ b/2.9/generated/torch.cuda.current_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.current_device<a class="headerlink" href="#torch-cuda-current-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.current_device">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">current_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.current_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">current_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.current_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the index of a currently selected device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.current_stream.html b/2.9/generated/torch.cuda.current_stream.html
index c14b2a94434..cae57920a4f 100644
--- a/2.9/generated/torch.cuda.current_stream.html
+++ b/2.9/generated/torch.cuda.current_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.current_stream<a class="headerlink" href="#torch-cuda-current-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.current_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1099"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.current_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1099"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.current_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the currently selected <a class="reference internal" href="torch.cuda.Stream.html#torch.cuda.Stream" title="torch.cuda.Stream"><code class="xref py py-class docutils literal notranslate"><span class="pre">Stream</span></code></a> for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.default_stream.html b/2.9/generated/torch.cuda.default_stream.html
index c249f6eb77b..57cea276e10 100644
--- a/2.9/generated/torch.cuda.default_stream.html
+++ b/2.9/generated/torch.cuda.default_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.default_stream<a class="headerlink" href="#torch-cuda-default-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.default_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">default_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.default_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">default_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.default_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the default <a class="reference internal" href="torch.cuda.Stream.html#torch.cuda.Stream" title="torch.cuda.Stream"><code class="xref py py-class docutils literal notranslate"><span class="pre">Stream</span></code></a> for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.device.html b/2.9/generated/torch.cuda.device.html
index 7273d14ed3a..39748afa118 100644
--- a/2.9/generated/torch.cuda.device.html
+++ b/2.9/generated/torch.cuda.device.html
@@ -4404,7 +4404,7 @@
 <h1>device<a class="headerlink" href="#device" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.device">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.device" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.device" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that changes the selected device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.device_count.html b/2.9/generated/torch.cuda.device_count.html
index 51e01f7a1cb..34c70aa1275 100644
--- a/2.9/generated/torch.cuda.device_count.html
+++ b/2.9/generated/torch.cuda.device_count.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.device_count<a class="headerlink" href="#torch-cuda-device-count" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.device_count">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1020"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.device_count" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1020"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.device_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the number of GPUs available.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.cuda.device_memory_used.html b/2.9/generated/torch.cuda.device_memory_used.html
index 67ce5b50111..924d04455e1 100644
--- a/2.9/generated/torch.cuda.device_memory_used.html
+++ b/2.9/generated/torch.cuda.device_memory_used.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.device_memory_used<a class="headerlink" href="#torch-cuda-device-memory-used" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.device_memory_used">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">device_memory_used</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.device_memory_used" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">device_memory_used</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.device_memory_used" title="Permalink to this definition">#</a></dt>
 <dd><p>Return used global (device) memory in bytes as given by <cite>nvidia-smi</cite> or <cite>amd-smi</cite>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.device_of.html b/2.9/generated/torch.cuda.device_of.html
index 6037a4576bd..ea0e12d48f7 100644
--- a/2.9/generated/torch.cuda.device_of.html
+++ b/2.9/generated/torch.cuda.device_of.html
@@ -4404,7 +4404,7 @@
 <h1>device_of<a class="headerlink" href="#device-of" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.device_of">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">device_of</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.device_of" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">device_of</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.device_of" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that changes the current device to that of given object.</p>
 <p>You can use both tensors and storages as arguments. If a given object is
 not allocated on a GPU, this is a no-op.</p>
diff --git a/2.9/generated/torch.cuda.gds.GdsFile.html b/2.9/generated/torch.cuda.gds.GdsFile.html
index 8fc3b425c4e..a0b7ae8b673 100644
--- a/2.9/generated/torch.cuda.gds.GdsFile.html
+++ b/2.9/generated/torch.cuda.gds.GdsFile.html
@@ -4404,7 +4404,7 @@
 <h1>GdsFile<a class="headerlink" href="#gdsfile" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.gds.GdsFile">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.gds.</span></span><span class="sig-name descname"><span class="pre">GdsFile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flags</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/gds.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.gds.</span></span><span class="sig-name descname"><span class="pre">GdsFile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flags</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/gds.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around cuFile.</p>
 <p>cuFile is a file-like interface to the GPUDirect Storage (GDS) API.</p>
 <p>See the <a class="reference external" href="https://docs.nvidia.com/gpudirect-storage/api-reference-guide/index.html#cufile-io-api">cufile docs</a>
@@ -4436,7 +4436,7 @@ <h1>GdsFile<a class="headerlink" href="#gdsfile" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.gds.GdsFile.deregister_handle">
-<span class="sig-name descname"><span class="pre">deregister_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/gds.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile.deregister_handle" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">deregister_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/gds.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile.deregister_handle" title="Permalink to this definition">#</a></dt>
 <dd><p>Deregisters file descriptor from cuFile Driver.</p>
 <p>This is a wrapper around <code class="docutils literal notranslate"><span class="pre">cuFileHandleDeregister</span></code>.</p>
 <dl class="field-list simple">
@@ -4445,7 +4445,7 @@ <h1>GdsFile<a class="headerlink" href="#gdsfile" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.gds.GdsFile.load_storage">
-<span class="sig-name descname"><span class="pre">load_storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">storage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/gds.py#L138"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile.load_storage" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">storage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/gds.py#L138"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile.load_storage" title="Permalink to this definition">#</a></dt>
 <dd><p>Loads data from the file into the storage.</p>
 <p>This is a wrapper around <code class="docutils literal notranslate"><span class="pre">cuFileRead</span></code>. <code class="docutils literal notranslate"><span class="pre">storage.nbytes()</span></code> of data
 will be loaded from the file at <code class="docutils literal notranslate"><span class="pre">offset</span></code> into the storage.</p>
@@ -4461,7 +4461,7 @@ <h1>GdsFile<a class="headerlink" href="#gdsfile" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.gds.GdsFile.register_handle">
-<span class="sig-name descname"><span class="pre">register_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/gds.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile.register_handle" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/gds.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile.register_handle" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers file descriptor to cuFile Driver.</p>
 <p>This is a wrapper around <code class="docutils literal notranslate"><span class="pre">cuFileHandleRegister</span></code>.</p>
 <dl class="field-list simple">
@@ -4470,7 +4470,7 @@ <h1>GdsFile<a class="headerlink" href="#gdsfile" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.gds.GdsFile.save_storage">
-<span class="sig-name descname"><span class="pre">save_storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">storage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/gds.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile.save_storage" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">storage</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/gds.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.GdsFile.save_storage" title="Permalink to this definition">#</a></dt>
 <dd><p>Saves data from the storage into the file.</p>
 <p>This is a wrapper around <code class="docutils literal notranslate"><span class="pre">cuFileWrite</span></code>. All bytes of the storage
 will be written to the file at <code class="docutils literal notranslate"><span class="pre">offset</span></code>.</p>
diff --git a/2.9/generated/torch.cuda.gds.gds_deregister_buffer.html b/2.9/generated/torch.cuda.gds.gds_deregister_buffer.html
index 329d8b60a1e..4dcdf150884 100644
--- a/2.9/generated/torch.cuda.gds.gds_deregister_buffer.html
+++ b/2.9/generated/torch.cuda.gds.gds_deregister_buffer.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.gds.gds_deregister_buffer<a class="headerlink" href="#torch-cuda-gds-gds-deregister-buffer" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.gds.gds_deregister_buffer">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.gds.</span></span><span class="sig-name descname"><span class="pre">gds_deregister_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">s</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/gds.py#L54"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.gds_deregister_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.gds.</span></span><span class="sig-name descname"><span class="pre">gds_deregister_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">s</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/gds.py#L54"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.gds_deregister_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>Deregisters a previously registered storage on a CUDA device as a cufile buffer.</p>
 <p>Example:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">src</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s2">&quot;cuda&quot;</span><span class="p">)</span>
diff --git a/2.9/generated/torch.cuda.gds.gds_register_buffer.html b/2.9/generated/torch.cuda.gds.gds_register_buffer.html
index 81116e90b30..8e00091f925 100644
--- a/2.9/generated/torch.cuda.gds.gds_register_buffer.html
+++ b/2.9/generated/torch.cuda.gds.gds_register_buffer.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.gds.gds_register_buffer<a class="headerlink" href="#torch-cuda-gds-gds-register-buffer" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.gds.gds_register_buffer">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.gds.</span></span><span class="sig-name descname"><span class="pre">gds_register_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">s</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/gds.py#L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.gds_register_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.gds.</span></span><span class="sig-name descname"><span class="pre">gds_register_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">s</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/gds.py#L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.gds.gds_register_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a storage on a CUDA device as a cufile buffer.</p>
 <p>Example:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">src</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s2">&quot;cuda&quot;</span><span class="p">)</span>
diff --git a/2.9/generated/torch.cuda.get_arch_list.html b/2.9/generated/torch.cuda.get_arch_list.html
index 2d378e6626f..f6c5e4d861e 100644
--- a/2.9/generated/torch.cuda.get_arch_list.html
+++ b/2.9/generated/torch.cuda.get_arch_list.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_arch_list<a class="headerlink" href="#torch-cuda-get-arch-list" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_arch_list">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_arch_list</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_arch_list" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_arch_list</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_arch_list" title="Permalink to this definition">#</a></dt>
 <dd><p>Return list CUDA architectures this library was compiled for.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.get_device_capability.html b/2.9/generated/torch.cuda.get_device_capability.html
index 21c70adb069..33632f93887 100644
--- a/2.9/generated/torch.cuda.get_device_capability.html
+++ b/2.9/generated/torch.cuda.get_device_capability.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_device_capability<a class="headerlink" href="#torch-cuda-get-device-capability" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_device_capability">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_device_capability</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L585"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_device_capability" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_device_capability</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L585"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_device_capability" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the cuda capability of a device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.get_device_name.html b/2.9/generated/torch.cuda.get_device_name.html
index 1b77fda2e18..be48fe7070e 100644
--- a/2.9/generated/torch.cuda.get_device_name.html
+++ b/2.9/generated/torch.cuda.get_device_name.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_device_name<a class="headerlink" href="#torch-cuda-get-device-name" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_device_name">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_device_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_device_name" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_device_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_device_name" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the name of a device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.get_device_properties.html b/2.9/generated/torch.cuda.get_device_properties.html
index 22ae9bf0d70..d0a80de34b8 100644
--- a/2.9/generated/torch.cuda.get_device_properties.html
+++ b/2.9/generated/torch.cuda.get_device_properties.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_device_properties<a class="headerlink" href="#torch-cuda-get-device-properties" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_device_properties">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_device_properties</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_device_properties" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_device_properties</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_device_properties" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the properties of a device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.get_gencode_flags.html b/2.9/generated/torch.cuda.get_gencode_flags.html
index 17e196f2fac..6dc149320d1 100644
--- a/2.9/generated/torch.cuda.get_gencode_flags.html
+++ b/2.9/generated/torch.cuda.get_gencode_flags.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_gencode_flags<a class="headerlink" href="#torch-cuda-get-gencode-flags" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_gencode_flags">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_gencode_flags</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1053"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_gencode_flags" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_gencode_flags</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1053"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_gencode_flags" title="Permalink to this definition">#</a></dt>
 <dd><p>Return NVCC gencode flags this library was compiled with.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.get_rng_state.html b/2.9/generated/torch.cuda.get_rng_state.html
index 2334940dddb..102d99c42cd 100644
--- a/2.9/generated/torch.cuda.get_rng_state.html
+++ b/2.9/generated/torch.cuda.get_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_rng_state<a class="headerlink" href="#torch-cuda-get-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L24"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the random number generator state of the specified GPU as a ByteTensor.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.get_rng_state_all.html b/2.9/generated/torch.cuda.get_rng_state_all.html
index 79ac000279f..cf91adc8a75 100644
--- a/2.9/generated/torch.cuda.get_rng_state_all.html
+++ b/2.9/generated/torch.cuda.get_rng_state_all.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_rng_state_all<a class="headerlink" href="#torch-cuda-get-rng-state-all" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_rng_state_all">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_rng_state_all</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_rng_state_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_rng_state_all</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_rng_state_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a list of ByteTensor representing the random number states of all devices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.get_stream_from_external.html b/2.9/generated/torch.cuda.get_stream_from_external.html
index ca3e4514d3d..58dc6cb7591 100644
--- a/2.9/generated/torch.cuda.get_stream_from_external.html
+++ b/2.9/generated/torch.cuda.get_stream_from_external.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_stream_from_external<a class="headerlink" href="#torch-cuda-get-stream-from-external" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_stream_from_external">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_stream_from_external</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_ptr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1135"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_stream_from_external" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_stream_from_external</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_ptr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1135"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_stream_from_external" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a <a class="reference internal" href="torch.cuda.Stream.html#torch.cuda.Stream" title="torch.cuda.Stream"><code class="xref py py-class docutils literal notranslate"><span class="pre">Stream</span></code></a> from an externally allocated CUDA stream.</p>
 <p>This function is used to wrap streams allocated in other libraries in order
 to facilitate data exchange and multi-library interactions.</p>
diff --git a/2.9/generated/torch.cuda.get_sync_debug_mode.html b/2.9/generated/torch.cuda.get_sync_debug_mode.html
index afca0891e96..8b498b0b472 100644
--- a/2.9/generated/torch.cuda.get_sync_debug_mode.html
+++ b/2.9/generated/torch.cuda.get_sync_debug_mode.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.get_sync_debug_mode<a class="headerlink" href="#torch-cuda-get-sync-debug-mode" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.get_sync_debug_mode">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_sync_debug_mode</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_sync_debug_mode" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">get_sync_debug_mode</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.get_sync_debug_mode" title="Permalink to this definition">#</a></dt>
 <dd><p>Return current value of debug mode for cuda synchronizing operations.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.graph.html b/2.9/generated/torch.cuda.graph.html
index f576744de05..88c5ab20287 100644
--- a/2.9/generated/torch.cuda.graph.html
+++ b/2.9/generated/torch.cuda.graph.html
@@ -4404,7 +4404,7 @@
 <h1>graph<a class="headerlink" href="#graph" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.graph">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cuda_graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capture_error_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'global'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.graph" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cuda_graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capture_error_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'global'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.graph" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that captures CUDA work into a <a class="reference internal" href="torch.cuda.CUDAGraph.html#torch.cuda.CUDAGraph" title="torch.cuda.CUDAGraph"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.cuda.CUDAGraph</span></code></a> object for later replay.</p>
 <p>See <a class="reference internal" href="../notes/cuda.html#cuda-graph-semantics"><span class="std std-ref">CUDA Graphs</span></a> for a general introduction,
 detailed use, and constraints.</p>
diff --git a/2.9/generated/torch.cuda.graph_pool_handle.html b/2.9/generated/torch.cuda.graph_pool_handle.html
index c5b67a47e53..98b26d9b6de 100644
--- a/2.9/generated/torch.cuda.graph_pool_handle.html
+++ b/2.9/generated/torch.cuda.graph_pool_handle.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.graph_pool_handle<a class="headerlink" href="#torch-cuda-graph-pool-handle" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.graph_pool_handle">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">graph_pool_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.graph_pool_handle" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">graph_pool_handle</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.graph_pool_handle" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an opaque token representing the id of a graph memory pool.</p>
 <p>See <a class="reference internal" href="../notes/cuda.html#graph-memory-management"><span class="std std-ref">Graph memory management</span></a>.</p>
 <div class="admonition warning">
diff --git a/2.9/generated/torch.cuda.init.html b/2.9/generated/torch.cuda.init.html
index b0410fc40bb..0720e74a593 100644
--- a/2.9/generated/torch.cuda.init.html
+++ b/2.9/generated/torch.cuda.init.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.init<a class="headerlink" href="#torch-cuda-init" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.init">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">init</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L368"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.init" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">init</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L368"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.init" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize PyTorch’s CUDA state.</p>
 <p>You may need to call this explicitly if you are interacting with
 PyTorch via its C API, as Python bindings for CUDA functionality
diff --git a/2.9/generated/torch.cuda.initial_seed.html b/2.9/generated/torch.cuda.initial_seed.html
index d5644f3e07c..29f6ee55425 100644
--- a/2.9/generated/torch.cuda.initial_seed.html
+++ b/2.9/generated/torch.cuda.initial_seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.initial_seed<a class="headerlink" href="#torch-cuda-initial-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.initial_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">initial_seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.initial_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">initial_seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.initial_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current random seed of the current GPU.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.cuda.ipc_collect.html b/2.9/generated/torch.cuda.ipc_collect.html
index 8191ab78182..b4b902be922 100644
--- a/2.9/generated/torch.cuda.ipc_collect.html
+++ b/2.9/generated/torch.cuda.ipc_collect.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.ipc_collect<a class="headerlink" href="#torch-cuda-ipc-collect" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.ipc_collect">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">ipc_collect</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ipc_collect" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">ipc_collect</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.ipc_collect" title="Permalink to this definition">#</a></dt>
 <dd><p>Force collects GPU memory after it has been released by CUDA IPC.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.cuda.is_available.html b/2.9/generated/torch.cuda.is_available.html
index 4782fc601b0..b97840f066d 100644
--- a/2.9/generated/torch.cuda.is_available.html
+++ b/2.9/generated/torch.cuda.is_available.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.is_available<a class="headerlink" href="#torch-cuda-is-available" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a bool indicating if CUDA is currently available.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.cuda.is_current_stream_capturing.html b/2.9/generated/torch.cuda.is_current_stream_capturing.html
index d68ef6732b1..1088f75dfd6 100644
--- a/2.9/generated/torch.cuda.is_current_stream_capturing.html
+++ b/2.9/generated/torch.cuda.is_current_stream_capturing.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.is_current_stream_capturing<a class="headerlink" href="#torch-cuda-is-current-stream-capturing" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.is_current_stream_capturing">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">is_current_stream_capturing</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.is_current_stream_capturing" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">is_current_stream_capturing</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.is_current_stream_capturing" title="Permalink to this definition">#</a></dt>
 <dd><p>Return True if CUDA graph capture is underway on the current CUDA stream, False otherwise.</p>
 <p>If a CUDA context does not exist on the current device, returns False without initializing the context.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cuda.is_initialized.html b/2.9/generated/torch.cuda.is_initialized.html
index c78ebbb3913..3799186579c 100644
--- a/2.9/generated/torch.cuda.is_initialized.html
+++ b/2.9/generated/torch.cuda.is_initialized.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.is_initialized<a class="headerlink" href="#torch-cuda-is-initialized" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.is_initialized">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">is_initialized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L333"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.is_initialized" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">is_initialized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L333"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.is_initialized" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether PyTorch’s CUDA state has been initialized.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.cuda.is_tf32_supported.html b/2.9/generated/torch.cuda.is_tf32_supported.html
index 22a0413a8dc..f1976be964e 100644
--- a/2.9/generated/torch.cuda.is_tf32_supported.html
+++ b/2.9/generated/torch.cuda.is_tf32_supported.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.is_tf32_supported<a class="headerlink" href="#torch-cuda-is-tf32-supported" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.is_tf32_supported">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">is_tf32_supported</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.is_tf32_supported" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">is_tf32_supported</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.is_tf32_supported" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a bool indicating if the current CUDA/ROCm device supports dtype tf32.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.jiterator._create_jit_fn.html b/2.9/generated/torch.cuda.jiterator._create_jit_fn.html
index 4d19c355fae..017784d116c 100644
--- a/2.9/generated/torch.cuda.jiterator._create_jit_fn.html
+++ b/2.9/generated/torch.cuda.jiterator._create_jit_fn.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.jiterator._create_jit_fn<a class="headerlink" href="#torch-cuda-jiterator-create-jit-fn" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.jiterator._create_jit_fn">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.jiterator.</span></span><span class="sig-name descname"><span class="pre">_create_jit_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code_string</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/jiterator.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.jiterator._create_jit_fn" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.jiterator.</span></span><span class="sig-name descname"><span class="pre">_create_jit_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code_string</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/jiterator.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.jiterator._create_jit_fn" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a jiterator-generated cuda kernel for an elementwise op.</p>
 <p>The code string has to be a valid CUDA function that describes the computation for a single element. The code
 string has to follow the c++ template pattern, as shown in the example below. This function will be inlined
diff --git a/2.9/generated/torch.cuda.jiterator._create_multi_output_jit_fn.html b/2.9/generated/torch.cuda.jiterator._create_multi_output_jit_fn.html
index 30ef0493771..cadb9a12b27 100644
--- a/2.9/generated/torch.cuda.jiterator._create_multi_output_jit_fn.html
+++ b/2.9/generated/torch.cuda.jiterator._create_multi_output_jit_fn.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.jiterator._create_multi_output_jit_fn<a class="headerlink" href="#torch-cuda-jiterator-create-multi-output-jit-fn" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.jiterator._create_multi_output_jit_fn">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.jiterator.</span></span><span class="sig-name descname"><span class="pre">_create_multi_output_jit_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code_string</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_outputs</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/jiterator.py#L161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.jiterator._create_multi_output_jit_fn" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.jiterator.</span></span><span class="sig-name descname"><span class="pre">_create_multi_output_jit_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code_string</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_outputs</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/jiterator.py#L161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.jiterator._create_multi_output_jit_fn" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a jiterator-generated cuda kernel for an elementwise op that supports returning one or more outputs.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.make_graphed_callables.html b/2.9/generated/torch.cuda.make_graphed_callables.html
index d5583be66ed..86bddd60439 100644
--- a/2.9/generated/torch.cuda.make_graphed_callables.html
+++ b/2.9/generated/torch.cuda.make_graphed_callables.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.make_graphed_callables<a class="headerlink" href="#torch-cuda-make-graphed-callables" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.make_graphed_callables">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">make_graphed_callables</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callables</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.14)"><span class="pre">object</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sample_args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_warmup_iters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_unused_input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">_POOL_HANDLE</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.14)"><span class="pre">object</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/graphs.py#L293"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.make_graphed_callables" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">make_graphed_callables</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callables</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.14)"><span class="pre">object</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sample_args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_warmup_iters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_unused_input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">_POOL_HANDLE</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.14)"><span class="pre">object</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/graphs.py#L293"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.make_graphed_callables" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">make_graphed_callables</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callables</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">torch.nn.modules.module.Module</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.14)"><span class="pre">object</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sample_args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_warmup_iters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_unused_input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pool</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">_POOL_HANDLE</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">torch.nn.modules.module.Module</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.14)"><span class="pre">object</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">]</span></span></span></span></dt>
 <dd><p>Accept callables (functions or <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.Module"><code class="xref py py-class docutils literal notranslate"><span class="pre">nn.Module</span></code></a>s) and returns graphed versions.</p>
diff --git a/2.9/generated/torch.cuda.manual_seed.html b/2.9/generated/torch.cuda.manual_seed.html
index 0b52dfaeba2..4f794d0b625 100644
--- a/2.9/generated/torch.cuda.manual_seed.html
+++ b/2.9/generated/torch.cuda.manual_seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.manual_seed<a class="headerlink" href="#torch-cuda-manual-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.manual_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.manual_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.manual_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the seed for generating random numbers for the current GPU.</p>
 <p>It’s safe to call this function if CUDA is not available; in that
 case, it is silently ignored.</p>
diff --git a/2.9/generated/torch.cuda.manual_seed_all.html b/2.9/generated/torch.cuda.manual_seed_all.html
index 24488e68289..29f069141c4 100644
--- a/2.9/generated/torch.cuda.manual_seed_all.html
+++ b/2.9/generated/torch.cuda.manual_seed_all.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.manual_seed_all<a class="headerlink" href="#torch-cuda-manual-seed-all" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.manual_seed_all">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">manual_seed_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L115"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.manual_seed_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">manual_seed_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L115"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.manual_seed_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the seed for generating random numbers on all GPUs.</p>
 <p>It’s safe to call this function if CUDA is not available; in that
 case, it is silently ignored.</p>
diff --git a/2.9/generated/torch.cuda.memory.CUDAPluggableAllocator.html b/2.9/generated/torch.cuda.memory.CUDAPluggableAllocator.html
index bf35c2bc530..b86380c0e13 100644
--- a/2.9/generated/torch.cuda.memory.CUDAPluggableAllocator.html
+++ b/2.9/generated/torch.cuda.memory.CUDAPluggableAllocator.html
@@ -4404,7 +4404,7 @@
 <h1>CUDAPluggableAllocator<a class="headerlink" href="#cudapluggableallocator" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.memory.CUDAPluggableAllocator">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">CUDAPluggableAllocator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path_to_so_file</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alloc_fn_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">free_fn_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L1104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.CUDAPluggableAllocator" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">CUDAPluggableAllocator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path_to_so_file</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alloc_fn_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">free_fn_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L1104"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.CUDAPluggableAllocator" title="Permalink to this definition">#</a></dt>
 <dd><p>CUDA memory allocator loaded from a so file.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.cuda.memory.MemPool.html b/2.9/generated/torch.cuda.memory.MemPool.html
index b75dafab472..f157c5ca5f5 100644
--- a/2.9/generated/torch.cuda.memory.MemPool.html
+++ b/2.9/generated/torch.cuda.memory.MemPool.html
@@ -4404,7 +4404,7 @@
 <h1>MemPool<a class="headerlink" href="#mempool" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.cuda.memory.MemPool">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">MemPool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L1159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.MemPool" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">MemPool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L1159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.MemPool" title="Permalink to this definition">#</a></dt>
 <dd><p>MemPool represents a pool of memory in a caching allocator. Currently,
 it’s just the ID of the pool object maintained in the CUDACachingAllocator.</p>
 <dl class="field-list simple">
@@ -4435,7 +4435,7 @@ <h1>MemPool<a class="headerlink" href="#mempool" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.memory.MemPool.snapshot">
-<span class="sig-name descname"><span class="pre">snapshot</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L1196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.MemPool.snapshot" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">snapshot</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L1196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.MemPool.snapshot" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a snapshot of the CUDA memory allocator pool state across all
 devices.</p>
 <p>Interpreting the output of this function requires familiarity with the
@@ -4449,7 +4449,7 @@ <h1>MemPool<a class="headerlink" href="#mempool" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.cuda.memory.MemPool.use_count">
-<span class="sig-name descname"><span class="pre">use_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L1192"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.MemPool.use_count" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">use_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L1192"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.MemPool.use_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the reference count of this pool.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.memory.caching_allocator_alloc.html b/2.9/generated/torch.cuda.memory.caching_allocator_alloc.html
index d6a052d436f..a4239d552da 100644
--- a/2.9/generated/torch.cuda.memory.caching_allocator_alloc.html
+++ b/2.9/generated/torch.cuda.memory.caching_allocator_alloc.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.caching_allocator_alloc<a class="headerlink" href="#torch-cuda-memory-caching-allocator-alloc" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.caching_allocator_alloc">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">caching_allocator_alloc</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.caching_allocator_alloc" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">caching_allocator_alloc</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L110"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.caching_allocator_alloc" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a memory allocation using the CUDA memory allocator.</p>
 <p>Memory is allocated for a given device and a stream, this
 function is intended to be used for interoperability with other
diff --git a/2.9/generated/torch.cuda.memory.caching_allocator_delete.html b/2.9/generated/torch.cuda.memory.caching_allocator_delete.html
index 4a6a1c92e66..c5c9e6d32a5 100644
--- a/2.9/generated/torch.cuda.memory.caching_allocator_delete.html
+++ b/2.9/generated/torch.cuda.memory.caching_allocator_delete.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.caching_allocator_delete<a class="headerlink" href="#torch-cuda-memory-caching-allocator-delete" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.caching_allocator_delete">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">caching_allocator_delete</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mem_ptr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.caching_allocator_delete" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">caching_allocator_delete</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mem_ptr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.caching_allocator_delete" title="Permalink to this definition">#</a></dt>
 <dd><p>Delete memory allocated using the CUDA memory allocator.</p>
 <p>Memory allocated with <code class="xref py py-func docutils literal notranslate"><span class="pre">caching_allocator_alloc()</span></code>.
 is freed here. The associated device and stream are tracked inside
diff --git a/2.9/generated/torch.cuda.memory.caching_allocator_enable.html b/2.9/generated/torch.cuda.memory.caching_allocator_enable.html
index fc3faa061f1..ed0e041281b 100644
--- a/2.9/generated/torch.cuda.memory.caching_allocator_enable.html
+++ b/2.9/generated/torch.cuda.memory.caching_allocator_enable.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.caching_allocator_enable<a class="headerlink" href="#torch-cuda-memory-caching-allocator-enable" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.caching_allocator_enable">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">caching_allocator_enable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.caching_allocator_enable" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">caching_allocator_enable</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.caching_allocator_enable" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable or disable the CUDA memory allocator. On by default.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.cuda.memory.change_current_allocator.html b/2.9/generated/torch.cuda.memory.change_current_allocator.html
index 1706822b426..7faa5a483fd 100644
--- a/2.9/generated/torch.cuda.memory.change_current_allocator.html
+++ b/2.9/generated/torch.cuda.memory.change_current_allocator.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.change_current_allocator<a class="headerlink" href="#torch-cuda-memory-change-current-allocator" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.change_current_allocator">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">change_current_allocator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">allocator</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L1136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.change_current_allocator" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">change_current_allocator</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">allocator</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L1136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.change_current_allocator" title="Permalink to this definition">#</a></dt>
 <dd><p>Change the currently used memory allocator to be the one provided.</p>
 <p>If the current allocator has already been used/initialized, this function will error.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cuda.memory.empty_cache.html b/2.9/generated/torch.cuda.memory.empty_cache.html
index 5e43b0f82a2..279700025e0 100644
--- a/2.9/generated/torch.cuda.memory.empty_cache.html
+++ b/2.9/generated/torch.cuda.memory.empty_cache.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.empty_cache<a class="headerlink" href="#torch-cuda-memory-empty-cache" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.empty_cache">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.empty_cache" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.empty_cache" title="Permalink to this definition">#</a></dt>
 <dd><p>Release all unoccupied cached memory currently held by the caching
 allocator so that those can be used in other GPU application and visible in
 <cite>nvidia-smi</cite>.</p>
diff --git a/2.9/generated/torch.cuda.memory.get_allocator_backend.html b/2.9/generated/torch.cuda.memory.get_allocator_backend.html
index 3b8921e4546..b406611eed5 100644
--- a/2.9/generated/torch.cuda.memory.get_allocator_backend.html
+++ b/2.9/generated/torch.cuda.memory.get_allocator_backend.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.get_allocator_backend<a class="headerlink" href="#torch-cuda-memory-get-allocator-backend" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.get_allocator_backend">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">get_allocator_backend</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L1082"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.get_allocator_backend" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">get_allocator_backend</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L1082"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.get_allocator_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a string describing the active allocator backend as set by
 <code class="docutils literal notranslate"><span class="pre">PYTORCH_CUDA_ALLOC_CONF</span></code>. Currently available backends are
 <code class="docutils literal notranslate"><span class="pre">native</span></code> (PyTorch’s native caching allocator) and <cite>cudaMallocAsync`</cite>
diff --git a/2.9/generated/torch.cuda.memory.get_per_process_memory_fraction.html b/2.9/generated/torch.cuda.memory.get_per_process_memory_fraction.html
index 8400bb38942..6f805e471dd 100644
--- a/2.9/generated/torch.cuda.memory.get_per_process_memory_fraction.html
+++ b/2.9/generated/torch.cuda.memory.get_per_process_memory_fraction.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.get_per_process_memory_fraction<a class="headerlink" href="#torch-cuda-memory-get-per-process-memory-fraction" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.get_per_process_memory_fraction">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">get_per_process_memory_fraction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.get_per_process_memory_fraction" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">get_per_process_memory_fraction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.get_per_process_memory_fraction" title="Permalink to this definition">#</a></dt>
 <dd><p>Get memory fraction for a process.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.memory.host_memory_stats.html b/2.9/generated/torch.cuda.memory.host_memory_stats.html
index 813742a59ca..6fb86c0c0b6 100644
--- a/2.9/generated/torch.cuda.memory.host_memory_stats.html
+++ b/2.9/generated/torch.cuda.memory.host_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.host_memory_stats<a class="headerlink" href="#torch-cuda-memory-host-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.host_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">host_memory_stats</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L379"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.host_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">host_memory_stats</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L379"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.host_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary of CUDA memory allocator statistics for a given device.</p>
 <blockquote>
 <div><p>The return value of this function is a dictionary of statistics, each of
diff --git a/2.9/generated/torch.cuda.memory.host_memory_stats_as_nested_dict.html b/2.9/generated/torch.cuda.memory.host_memory_stats_as_nested_dict.html
index de0a227c4d3..6fc783d03b8 100644
--- a/2.9/generated/torch.cuda.memory.host_memory_stats_as_nested_dict.html
+++ b/2.9/generated/torch.cuda.memory.host_memory_stats_as_nested_dict.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.host_memory_stats_as_nested_dict<a class="headerlink" href="#torch-cuda-memory-host-memory-stats-as-nested-dict" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.host_memory_stats_as_nested_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">host_memory_stats_as_nested_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.host_memory_stats_as_nested_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">host_memory_stats_as_nested_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.host_memory_stats_as_nested_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the result of <code class="xref py py-func docutils literal notranslate"><span class="pre">host_memory_stats()</span></code> as a nested dictionary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.memory.list_gpu_processes.html b/2.9/generated/torch.cuda.memory.list_gpu_processes.html
index c7086d339a8..280780d8fe5 100644
--- a/2.9/generated/torch.cuda.memory.list_gpu_processes.html
+++ b/2.9/generated/torch.cuda.memory.list_gpu_processes.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.list_gpu_processes<a class="headerlink" href="#torch-cuda-memory-list-gpu-processes" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.list_gpu_processes">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">list_gpu_processes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L757"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.list_gpu_processes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">list_gpu_processes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L757"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.list_gpu_processes" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a human-readable printout of the running processes and their GPU memory use for a given device.</p>
 <p>This can be useful to display periodically during training, or when
 handling out-of-memory exceptions.</p>
diff --git a/2.9/generated/torch.cuda.memory.max_memory_allocated.html b/2.9/generated/torch.cuda.memory.max_memory_allocated.html
index f68e19f68e3..8ab0e533cab 100644
--- a/2.9/generated/torch.cuda.memory.max_memory_allocated.html
+++ b/2.9/generated/torch.cuda.memory.max_memory_allocated.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.max_memory_allocated<a class="headerlink" href="#torch-cuda-memory-max-memory-allocated" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.max_memory_allocated">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L542"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.max_memory_allocated" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L542"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.max_memory_allocated" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the maximum GPU memory occupied by tensors in bytes for a given device.</p>
 <p>By default, this returns the peak allocated memory since the beginning of
 this program. <code class="xref py py-func docutils literal notranslate"><span class="pre">reset_peak_memory_stats()</span></code> can be used to
diff --git a/2.9/generated/torch.cuda.memory.max_memory_cached.html b/2.9/generated/torch.cuda.memory.max_memory_cached.html
index 8e728abb061..52d53ad609a 100644
--- a/2.9/generated/torch.cuda.memory.max_memory_cached.html
+++ b/2.9/generated/torch.cuda.memory.max_memory_cached.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.max_memory_cached<a class="headerlink" href="#torch-cuda-memory-max-memory-cached" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.max_memory_cached">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_cached</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L608"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.max_memory_cached" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_cached</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L608"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.max_memory_cached" title="Permalink to this definition">#</a></dt>
 <dd><p>Deprecated; see <code class="xref py py-func docutils literal notranslate"><span class="pre">max_memory_reserved()</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.memory.max_memory_reserved.html b/2.9/generated/torch.cuda.memory.max_memory_reserved.html
index 436a56dcc4b..58f95ec7083 100644
--- a/2.9/generated/torch.cuda.memory.max_memory_reserved.html
+++ b/2.9/generated/torch.cuda.memory.max_memory_reserved.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.max_memory_reserved<a class="headerlink" href="#torch-cuda-memory-max-memory-reserved" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.max_memory_reserved">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.max_memory_reserved" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.max_memory_reserved" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the maximum GPU memory managed by the caching allocator in bytes for a given device.</p>
 <p>By default, this returns the peak cached memory since the beginning of this
 program. <code class="xref py py-func docutils literal notranslate"><span class="pre">reset_peak_memory_stats()</span></code> can be used to reset
diff --git a/2.9/generated/torch.cuda.memory.mem_get_info.html b/2.9/generated/torch.cuda.memory.mem_get_info.html
index 7575f0bcef5..52d12392515 100644
--- a/2.9/generated/torch.cuda.memory.mem_get_info.html
+++ b/2.9/generated/torch.cuda.memory.mem_get_info.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.mem_get_info<a class="headerlink" href="#torch-cuda-memory-mem-get-info" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.mem_get_info">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">mem_get_info</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L822"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.mem_get_info" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">mem_get_info</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L822"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.mem_get_info" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the global free and total GPU memory for a given device using cudaMemGetInfo.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.memory.memory_allocated.html b/2.9/generated/torch.cuda.memory.memory_allocated.html
index 70fe3ee9ca9..f27625b4164 100644
--- a/2.9/generated/torch.cuda.memory.memory_allocated.html
+++ b/2.9/generated/torch.cuda.memory.memory_allocated.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.memory_allocated<a class="headerlink" href="#torch-cuda-memory-memory-allocated" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.memory_allocated">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_allocated" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_allocated" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current GPU memory occupied by tensors in bytes for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.memory.memory_cached.html b/2.9/generated/torch.cuda.memory.memory_cached.html
index 69e027e67be..38cf9bf8f9e 100644
--- a/2.9/generated/torch.cuda.memory.memory_cached.html
+++ b/2.9/generated/torch.cuda.memory.memory_cached.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.memory_cached<a class="headerlink" href="#torch-cuda-memory-memory-cached" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.memory_cached">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_cached</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L599"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_cached" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_cached</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L599"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_cached" title="Permalink to this definition">#</a></dt>
 <dd><p>Deprecated; see <code class="xref py py-func docutils literal notranslate"><span class="pre">memory_reserved()</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.memory.memory_reserved.html b/2.9/generated/torch.cuda.memory.memory_reserved.html
index 1dffa8bed58..4f88dbd6e3a 100644
--- a/2.9/generated/torch.cuda.memory.memory_reserved.html
+++ b/2.9/generated/torch.cuda.memory.memory_reserved.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.memory_reserved<a class="headerlink" href="#torch-cuda-memory-memory-reserved" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.memory_reserved">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L563"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_reserved" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L563"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_reserved" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current GPU memory managed by the caching allocator in bytes for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.memory.memory_snapshot.html b/2.9/generated/torch.cuda.memory.memory_snapshot.html
index d1c491c8b5b..b210e60f845 100644
--- a/2.9/generated/torch.cuda.memory.memory_snapshot.html
+++ b/2.9/generated/torch.cuda.memory.memory_snapshot.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.memory_snapshot<a class="headerlink" href="#torch-cuda-memory-memory-snapshot" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.memory_snapshot">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_snapshot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mempool_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_snapshot" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_snapshot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mempool_id</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_snapshot" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a snapshot of the CUDA memory allocator state across all devices.</p>
 <p>Interpreting the output of this function requires familiarity with the
 memory allocator internals.</p>
diff --git a/2.9/generated/torch.cuda.memory.memory_stats.html b/2.9/generated/torch.cuda.memory.memory_stats.html
index 06bcda3e484..807bdbac310 100644
--- a/2.9/generated/torch.cuda.memory.memory_stats.html
+++ b/2.9/generated/torch.cuda.memory.memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.memory_stats<a class="headerlink" href="#torch-cuda-memory-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary of CUDA memory allocator statistics for a given device.</p>
 <p>The return value of this function is a dictionary of statistics, each of
 which is a non-negative integer.</p>
diff --git a/2.9/generated/torch.cuda.memory.memory_stats_as_nested_dict.html b/2.9/generated/torch.cuda.memory.memory_stats_as_nested_dict.html
index 02f926039c3..6a59a96306c 100644
--- a/2.9/generated/torch.cuda.memory.memory_stats_as_nested_dict.html
+++ b/2.9/generated/torch.cuda.memory.memory_stats_as_nested_dict.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.memory_stats_as_nested_dict<a class="headerlink" href="#torch-cuda-memory-memory-stats-as-nested-dict" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.memory_stats_as_nested_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats_as_nested_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_stats_as_nested_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats_as_nested_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_stats_as_nested_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the result of <code class="xref py py-func docutils literal notranslate"><span class="pre">memory_stats()</span></code> as a nested dictionary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.cuda.memory.memory_summary.html b/2.9/generated/torch.cuda.memory.memory_summary.html
index 917e8950ab7..2c52288d829 100644
--- a/2.9/generated/torch.cuda.memory.memory_summary.html
+++ b/2.9/generated/torch.cuda.memory.memory_summary.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.memory_summary<a class="headerlink" href="#torch-cuda-memory-memory-summary" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.memory_summary">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_summary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">abbreviated</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L630"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_summary" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">memory_summary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">abbreviated</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L630"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.memory_summary" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a human-readable printout of the current memory allocator statistics for a given device.</p>
 <p>This can be useful to display periodically during training, or when
 handling out-of-memory exceptions.</p>
diff --git a/2.9/generated/torch.cuda.memory.reset_accumulated_host_memory_stats.html b/2.9/generated/torch.cuda.memory.reset_accumulated_host_memory_stats.html
index e225e64407e..012242ed752 100644
--- a/2.9/generated/torch.cuda.memory.reset_accumulated_host_memory_stats.html
+++ b/2.9/generated/torch.cuda.memory.reset_accumulated_host_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.reset_accumulated_host_memory_stats<a class="headerlink" href="#torch-cuda-memory-reset-accumulated-host-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.reset_accumulated_host_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_accumulated_host_memory_stats</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L455"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_accumulated_host_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_accumulated_host_memory_stats</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L455"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_accumulated_host_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the “accumulated” (historical) stats tracked by the host memory allocator.</p>
 <p>See <code class="xref py py-func docutils literal notranslate"><span class="pre">host_memory_stats()</span></code> for details. Accumulated stats correspond to
 the <cite>“allocated”</cite> and <cite>“freed”</cite> keys in each individual stat dict.</p>
diff --git a/2.9/generated/torch.cuda.memory.reset_accumulated_memory_stats.html b/2.9/generated/torch.cuda.memory.reset_accumulated_memory_stats.html
index b8353705343..15e70b33528 100644
--- a/2.9/generated/torch.cuda.memory.reset_accumulated_memory_stats.html
+++ b/2.9/generated/torch.cuda.memory.reset_accumulated_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.reset_accumulated_memory_stats<a class="headerlink" href="#torch-cuda-memory-reset-accumulated-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.reset_accumulated_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_accumulated_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_accumulated_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_accumulated_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_accumulated_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the “accumulated” (historical) stats tracked by the CUDA memory allocator.</p>
 <p>See <code class="xref py py-func docutils literal notranslate"><span class="pre">memory_stats()</span></code> for details. Accumulated stats correspond to
 the <cite>“allocated”</cite> and <cite>“freed”</cite> keys in each individual stat dict, as well as
diff --git a/2.9/generated/torch.cuda.memory.reset_max_memory_allocated.html b/2.9/generated/torch.cuda.memory.reset_max_memory_allocated.html
index 6489b1bc5e7..4b7dd22f4dd 100644
--- a/2.9/generated/torch.cuda.memory.reset_max_memory_allocated.html
+++ b/2.9/generated/torch.cuda.memory.reset_max_memory_allocated.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.reset_max_memory_allocated<a class="headerlink" href="#torch-cuda-memory-reset-max-memory-allocated" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.reset_max_memory_allocated">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_max_memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_max_memory_allocated" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_max_memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_max_memory_allocated" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the starting point in tracking maximum GPU memory occupied by tensors for a given device.</p>
 <p>See <code class="xref py py-func docutils literal notranslate"><span class="pre">max_memory_allocated()</span></code> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cuda.memory.reset_max_memory_cached.html b/2.9/generated/torch.cuda.memory.reset_max_memory_cached.html
index 60c30b680d4..71f84f494bf 100644
--- a/2.9/generated/torch.cuda.memory.reset_max_memory_cached.html
+++ b/2.9/generated/torch.cuda.memory.reset_max_memory_cached.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.reset_max_memory_cached<a class="headerlink" href="#torch-cuda-memory-reset-max-memory-cached" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.reset_max_memory_cached">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_max_memory_cached</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L499"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_max_memory_cached" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_max_memory_cached</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L499"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_max_memory_cached" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the starting point in tracking maximum GPU memory managed by the caching allocator for a given device.</p>
 <p>See <code class="xref py py-func docutils literal notranslate"><span class="pre">max_memory_cached()</span></code> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cuda.memory.reset_peak_host_memory_stats.html b/2.9/generated/torch.cuda.memory.reset_peak_host_memory_stats.html
index abe31abe6e4..587aecf570c 100644
--- a/2.9/generated/torch.cuda.memory.reset_peak_host_memory_stats.html
+++ b/2.9/generated/torch.cuda.memory.reset_peak_host_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.reset_peak_host_memory_stats<a class="headerlink" href="#torch-cuda-memory-reset-peak-host-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.reset_peak_host_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_peak_host_memory_stats</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L464"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_peak_host_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_peak_host_memory_stats</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L464"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_peak_host_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the “peak” stats tracked by the host memory allocator.</p>
 <p>See <code class="xref py py-func docutils literal notranslate"><span class="pre">host_memory_stats()</span></code> for details. Peak stats correspond to the
 <cite>“peak”</cite> key in each individual stat dict.</p>
diff --git a/2.9/generated/torch.cuda.memory.reset_peak_memory_stats.html b/2.9/generated/torch.cuda.memory.reset_peak_memory_stats.html
index 37d039de614..96ff9bd5ef9 100644
--- a/2.9/generated/torch.cuda.memory.reset_peak_memory_stats.html
+++ b/2.9/generated/torch.cuda.memory.reset_peak_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.reset_peak_memory_stats<a class="headerlink" href="#torch-cuda-memory-reset-peak-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.reset_peak_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_peak_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L360"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_peak_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">reset_peak_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L360"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.reset_peak_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the “peak” stats tracked by the CUDA memory allocator.</p>
 <p>See <code class="xref py py-func docutils literal notranslate"><span class="pre">memory_stats()</span></code> for details. Peak stats correspond to the
 <cite>“peak”</cite> key in each individual stat dict.</p>
diff --git a/2.9/generated/torch.cuda.memory.set_per_process_memory_fraction.html b/2.9/generated/torch.cuda.memory.set_per_process_memory_fraction.html
index bdce038c8df..ba40284e826 100644
--- a/2.9/generated/torch.cuda.memory.set_per_process_memory_fraction.html
+++ b/2.9/generated/torch.cuda.memory.set_per_process_memory_fraction.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory.set_per_process_memory_fraction<a class="headerlink" href="#torch-cuda-memory-set-per-process-memory-fraction" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory.set_per_process_memory_fraction">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">set_per_process_memory_fraction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fraction</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.set_per_process_memory_fraction" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">set_per_process_memory_fraction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fraction</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory.set_per_process_memory_fraction" title="Permalink to this definition">#</a></dt>
 <dd><p>Set memory fraction for a process.</p>
 <p>The fraction is used to limit an caching allocator to allocated memory on a CUDA device.
 The allowed value equals the total visible memory multiplied fraction.
diff --git a/2.9/generated/torch.cuda.memory_usage.html b/2.9/generated/torch.cuda.memory_usage.html
index bf358a102a7..d061f7d1824 100644
--- a/2.9/generated/torch.cuda.memory_usage.html
+++ b/2.9/generated/torch.cuda.memory_usage.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.memory_usage<a class="headerlink" href="#torch-cuda-memory-usage" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory_usage">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">memory_usage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1324"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory_usage" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">memory_usage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1324"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory_usage" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the percent of time over the past sample period during which global (device)
 memory was being read or written as given by <cite>nvidia-smi</cite>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cuda.nvtx.mark.html b/2.9/generated/torch.cuda.nvtx.mark.html
index 6dcb767e6a6..0a2caa665c4 100644
--- a/2.9/generated/torch.cuda.nvtx.mark.html
+++ b/2.9/generated/torch.cuda.nvtx.mark.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.nvtx.mark<a class="headerlink" href="#torch-cuda-nvtx-mark" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.nvtx.mark">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.nvtx.</span></span><span class="sig-name descname"><span class="pre">mark</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/nvtx.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.nvtx.mark" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.nvtx.</span></span><span class="sig-name descname"><span class="pre">mark</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/nvtx.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.nvtx.mark" title="Permalink to this definition">#</a></dt>
 <dd><p>Describe an instantaneous event that occurred at some point.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.nvtx.range.html b/2.9/generated/torch.cuda.nvtx.range.html
index 04d3f42c789..0f61b7ec6a6 100644
--- a/2.9/generated/torch.cuda.nvtx.range.html
+++ b/2.9/generated/torch.cuda.nvtx.range.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.nvtx.range<a class="headerlink" href="#torch-cuda-nvtx-range" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.nvtx.range">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.nvtx.</span></span><span class="sig-name descname"><span class="pre">range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/nvtx.py#L111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.nvtx.range" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.nvtx.</span></span><span class="sig-name descname"><span class="pre">range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/nvtx.py#L111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.nvtx.range" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager / decorator that pushes an NVTX range at the beginning
 of its scope, and pops it at the end. If extra arguments are given,
 they are passed as arguments to msg.format().</p>
diff --git a/2.9/generated/torch.cuda.nvtx.range_pop.html b/2.9/generated/torch.cuda.nvtx.range_pop.html
index c917ce9fbe6..cf26b324891 100644
--- a/2.9/generated/torch.cuda.nvtx.range_pop.html
+++ b/2.9/generated/torch.cuda.nvtx.range_pop.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.nvtx.range_pop<a class="headerlink" href="#torch-cuda-nvtx-range-pop" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.nvtx.range_pop">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.nvtx.</span></span><span class="sig-name descname"><span class="pre">range_pop</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/nvtx.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.nvtx.range_pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.nvtx.</span></span><span class="sig-name descname"><span class="pre">range_pop</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/nvtx.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.nvtx.range_pop" title="Permalink to this definition">#</a></dt>
 <dd><p>Pop a range off of a stack of nested range spans.  Returns the  zero-based depth of the range that is ended.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.cuda.nvtx.range_push.html b/2.9/generated/torch.cuda.nvtx.range_push.html
index 0162afd731d..990b927004b 100644
--- a/2.9/generated/torch.cuda.nvtx.range_push.html
+++ b/2.9/generated/torch.cuda.nvtx.range_push.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.nvtx.range_push<a class="headerlink" href="#torch-cuda-nvtx-range-push" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.nvtx.range_push">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.nvtx.</span></span><span class="sig-name descname"><span class="pre">range_push</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/nvtx.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.nvtx.range_push" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.nvtx.</span></span><span class="sig-name descname"><span class="pre">range_push</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/nvtx.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.nvtx.range_push" title="Permalink to this definition">#</a></dt>
 <dd><p>Push a range onto a stack of nested range span.  Returns zero-based depth of the range that is started.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.power_draw.html b/2.9/generated/torch.cuda.power_draw.html
index ee593292bd9..431b64d4ee5 100644
--- a/2.9/generated/torch.cuda.power_draw.html
+++ b/2.9/generated/torch.cuda.power_draw.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.power_draw<a class="headerlink" href="#torch-cuda-power-draw" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.power_draw">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">power_draw</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1387"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.power_draw" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">power_draw</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1387"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.power_draw" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Return the average power draw of the GPU sensor in mW (MilliWatts)</dt><dd><p>over the past sample period as given by <cite>nvidia-smi</cite> for Fermi or newer fully supported devices.</p>
 </dd>
diff --git a/2.9/generated/torch.cuda.seed.html b/2.9/generated/torch.cuda.seed.html
index ce5bae9577e..40f0a2eb5ed 100644
--- a/2.9/generated/torch.cuda.seed.html
+++ b/2.9/generated/torch.cuda.seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.seed<a class="headerlink" href="#torch-cuda-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.seed">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the seed for generating random numbers to a random number for the current GPU.</p>
 <p>It’s safe to call this function if CUDA is not available; in that
 case, it is silently ignored.</p>
diff --git a/2.9/generated/torch.cuda.seed_all.html b/2.9/generated/torch.cuda.seed_all.html
index 3e9a86cd6f1..dfd95d31e6d 100644
--- a/2.9/generated/torch.cuda.seed_all.html
+++ b/2.9/generated/torch.cuda.seed_all.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.seed_all<a class="headerlink" href="#torch-cuda-seed-all" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.seed_all">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">seed_all</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.seed_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">seed_all</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.seed_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the seed for generating random numbers to a random number on all GPUs.</p>
 <p>It’s safe to call this function if CUDA is not available; in that
 case, it is silently ignored.</p>
diff --git a/2.9/generated/torch.cuda.set_device.html b/2.9/generated/torch.cuda.set_device.html
index 9cf7e554b02..6d5fc0eed2b 100644
--- a/2.9/generated/torch.cuda.set_device.html
+++ b/2.9/generated/torch.cuda.set_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.set_device<a class="headerlink" href="#torch-cuda-set-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.set_device">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L555"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L555"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the current device.</p>
 <p>Usage of this function is discouraged in favor of <a class="reference internal" href="torch.cuda.device.html#torch.cuda.device" title="torch.cuda.device"><code class="xref any py py-class docutils literal notranslate"><span class="pre">device</span></code></a>. In most
 cases it’s better to use <code class="docutils literal notranslate"><span class="pre">CUDA_VISIBLE_DEVICES</span></code> environmental variable.</p>
diff --git a/2.9/generated/torch.cuda.set_rng_state.html b/2.9/generated/torch.cuda.set_rng_state.html
index 7d8743e189d..b70b8db1cb8 100644
--- a/2.9/generated/torch.cuda.set_rng_state.html
+++ b/2.9/generated/torch.cuda.set_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.set_rng_state<a class="headerlink" href="#torch-cuda-set-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.set_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the random number generator state of the specified GPU.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.set_rng_state_all.html b/2.9/generated/torch.cuda.set_rng_state_all.html
index 8d1f6ffd113..24ce201c713 100644
--- a/2.9/generated/torch.cuda.set_rng_state_all.html
+++ b/2.9/generated/torch.cuda.set_rng_state_all.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.set_rng_state_all<a class="headerlink" href="#torch-cuda-set-rng-state-all" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.set_rng_state_all">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_rng_state_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_states</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/random.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_rng_state_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_rng_state_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_states</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/random.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_rng_state_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the random number generator state of all devices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.set_stream.html b/2.9/generated/torch.cuda.set_stream.html
index 435fda08e3b..4a93e53f972 100644
--- a/2.9/generated/torch.cuda.set_stream.html
+++ b/2.9/generated/torch.cuda.set_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.set_stream<a class="headerlink" href="#torch-cuda-set-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.set_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L718"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L718"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_stream" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Set the current stream.This is a wrapper API to set the stream.</dt><dd><p>Usage of this function is discouraged in favor of the <code class="docutils literal notranslate"><span class="pre">stream</span></code>
 context manager.</p>
diff --git a/2.9/generated/torch.cuda.set_sync_debug_mode.html b/2.9/generated/torch.cuda.set_sync_debug_mode.html
index c9ce3d6bcbc..6657abd252b 100644
--- a/2.9/generated/torch.cuda.set_sync_debug_mode.html
+++ b/2.9/generated/torch.cuda.set_sync_debug_mode.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.set_sync_debug_mode<a class="headerlink" href="#torch-cuda-set-sync-debug-mode" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.set_sync_debug_mode">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_sync_debug_mode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">debug_mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_sync_debug_mode" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">set_sync_debug_mode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">debug_mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.set_sync_debug_mode" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the debug mode for cuda synchronizing operations.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.stream.html b/2.9/generated/torch.cuda.stream.html
index 2bae494fe23..0ee08349e9c 100644
--- a/2.9/generated/torch.cuda.stream.html
+++ b/2.9/generated/torch.cuda.stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.stream<a class="headerlink" href="#torch-cuda-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.stream">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L690"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L690"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrap around the Context-manager StreamContext that selects a given stream.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.synchronize.html b/2.9/generated/torch.cuda.synchronize.html
index 011dff83bbf..137aa5ccd4f 100644
--- a/2.9/generated/torch.cuda.synchronize.html
+++ b/2.9/generated/torch.cuda.synchronize.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.synchronize<a class="headerlink" href="#torch-cuda-synchronize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.synchronize">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1073"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1073"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait for all kernels in all streams on a CUDA device to complete.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.cuda.temperature.html b/2.9/generated/torch.cuda.temperature.html
index 00518a71692..1385002be48 100644
--- a/2.9/generated/torch.cuda.temperature.html
+++ b/2.9/generated/torch.cuda.temperature.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.temperature<a class="headerlink" href="#torch-cuda-temperature" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.temperature">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">temperature</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1366"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.temperature" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">temperature</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1366"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.temperature" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the average temperature of the GPU sensor in Degrees C (Centigrades).</p>
 <p>The average temperature is computed based on past sample period as given by <cite>nvidia-smi</cite>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.cuda.utilization.html b/2.9/generated/torch.cuda.utilization.html
index d07b2988dda..48688953a7b 100644
--- a/2.9/generated/torch.cuda.utilization.html
+++ b/2.9/generated/torch.cuda.utilization.html
@@ -4404,7 +4404,7 @@
 <h1>torch.cuda.utilization<a class="headerlink" href="#torch-cuda-utilization" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.utilization">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">utilization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/__init__.py#L1345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.utilization" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.</span></span><span class="sig-name descname"><span class="pre">utilization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/__init__.py#L1345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.utilization" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the percent of time over the past sample period during which one or
 more kernels was executing on the GPU as given by <cite>nvidia-smi</cite>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.einsum.html b/2.9/generated/torch.einsum.html
index c4a54606ce6..641e7c7f6d7 100644
--- a/2.9/generated/torch.einsum.html
+++ b/2.9/generated/torch.einsum.html
@@ -4404,7 +4404,7 @@
 <h1>torch.einsum<a class="headerlink" href="#torch-einsum" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.einsum">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">einsum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">equation</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">operands</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.einsum" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">einsum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">equation</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">operands</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.einsum" title="Permalink to this definition">#</a></dt>
 <dd><p>Sums the product of the elements of the input <code class="xref py py-attr docutils literal notranslate"><span class="pre">operands</span></code> along dimensions specified using a notation
 based on the Einstein summation convention.</p>
 <p>Einsum allows computing many common multi-dimensional linear algebraic array operations by representing them
diff --git a/2.9/generated/torch.enable_grad.html b/2.9/generated/torch.enable_grad.html
index 2f1a4f7fa05..f6790e252d9 100644
--- a/2.9/generated/torch.enable_grad.html
+++ b/2.9/generated/torch.enable_grad.html
@@ -4404,7 +4404,7 @@
 <h1>enable_grad<a class="headerlink" href="#enable-grad" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.enable_grad">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">enable_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">orig_func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/grad_mode.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.enable_grad" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">enable_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">orig_func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/grad_mode.py#L88"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.enable_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that enables gradient calculation.</p>
 <p>Enables gradient calculation, if it has been disabled via <a class="reference internal" href="torch.no_grad.html#torch.no_grad" title="torch.no_grad"><code class="xref py py-class docutils literal notranslate"><span class="pre">no_grad</span></code></a>
 or <code class="xref py py-class docutils literal notranslate"><span class="pre">set_grad_enabled</span></code>.</p>
diff --git a/2.9/generated/torch.from_dlpack.html b/2.9/generated/torch.from_dlpack.html
index 177490a4593..ab49e0576b4 100644
--- a/2.9/generated/torch.from_dlpack.html
+++ b/2.9/generated/torch.from_dlpack.html
@@ -4404,7 +4404,7 @@
 <h1>torch.from_dlpack<a class="headerlink" href="#torch-from-dlpack" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.from_dlpack">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">from_dlpack</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ext_tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/dlpack.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.from_dlpack" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">from_dlpack</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ext_tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/dlpack.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.from_dlpack" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts a tensor from an external library into a <code class="docutils literal notranslate"><span class="pre">torch.Tensor</span></code>.</p>
 <p>The returned PyTorch tensor will share the memory with the input tensor
 (which may have come from another library). Note that in-place operations
diff --git a/2.9/generated/torch.func.debug_unwrap.html b/2.9/generated/torch.func.debug_unwrap.html
index 1c8351d05a6..104eb9d3e90 100644
--- a/2.9/generated/torch.func.debug_unwrap.html
+++ b/2.9/generated/torch.func.debug_unwrap.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.debug_unwrap<a class="headerlink" href="#torch-func-debug-unwrap" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.debug_unwrap">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">debug_unwrap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/eager_transforms.py#L1803"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.debug_unwrap" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">debug_unwrap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/eager_transforms.py#L1803"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.debug_unwrap" title="Permalink to this definition">#</a></dt>
 <dd><p>Unwraps a functorch tensor (e.g. BatchedTensor, GradTrackingTensor) to its underlying tensor.</p>
 <p>This function should only be used in a debug setting (e.g. trying to print the
 value of a Tensor in a debugger). Otherwise, using the result of function
diff --git a/2.9/generated/torch.func.functional_call.html b/2.9/generated/torch.func.functional_call.html
index 4fa4a0aa71a..738b8964444 100644
--- a/2.9/generated/torch.func.functional_call.html
+++ b/2.9/generated/torch.func.functional_call.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.functional_call<a class="headerlink" href="#torch-func-functional-call" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.functional_call">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">functional_call</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameter_and_buffer_dicts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/functional_call.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.functional_call" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">functional_call</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameter_and_buffer_dicts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/functional_call.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.functional_call" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs a functional call on the module by replacing the module parameters
 and buffers with the provided ones.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.func.functionalize.html b/2.9/generated/torch.func.functionalize.html
index 9b76c826b9b..c57162f46b2 100644
--- a/2.9/generated/torch.func.functionalize.html
+++ b/2.9/generated/torch.func.functionalize.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.functionalize<a class="headerlink" href="#torch-func-functionalize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.functionalize">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">functionalize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mutations'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/eager_transforms.py#L1464"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.functionalize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">functionalize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mutations'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/eager_transforms.py#L1464"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.functionalize" title="Permalink to this definition">#</a></dt>
 <dd><p>functionalize is a transform that can be used to remove (intermediate)
 mutations and aliasing from a function, while preserving the function’s
 semantics.</p>
diff --git a/2.9/generated/torch.func.grad.html b/2.9/generated/torch.func.grad.html
index 9ee22966e97..588a709cfe6 100644
--- a/2.9/generated/torch.func.grad.html
+++ b/2.9/generated/torch.func.grad.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.grad<a class="headerlink" href="#torch-func-grad" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.grad">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/apis.py#L304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/apis.py#L304"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.grad" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">grad</span></code> operator helps computing gradients of <code class="docutils literal notranslate"><span class="pre">func</span></code> with respect to the
 input(s) specified by <code class="docutils literal notranslate"><span class="pre">argnums</span></code>. This operator can be nested to
 compute higher-order gradients.</p>
diff --git a/2.9/generated/torch.func.grad_and_value.html b/2.9/generated/torch.func.grad_and_value.html
index fced6808ed5..133bf0c16d7 100644
--- a/2.9/generated/torch.func.grad_and_value.html
+++ b/2.9/generated/torch.func.grad_and_value.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.grad_and_value<a class="headerlink" href="#torch-func-grad-and-value" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.grad_and_value">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">grad_and_value</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/apis.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.grad_and_value" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">grad_and_value</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/apis.py#L414"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.grad_and_value" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a function to compute a tuple of the gradient and primal, or
 forward, computation.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.func.hessian.html b/2.9/generated/torch.func.hessian.html
index fd9299efb7f..cf4c559da40 100644
--- a/2.9/generated/torch.func.hessian.html
+++ b/2.9/generated/torch.func.hessian.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.hessian<a class="headerlink" href="#torch-func-hessian" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.hessian">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">hessian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/eager_transforms.py#L1310"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.hessian" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">hessian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/eager_transforms.py#L1310"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.hessian" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the Hessian of <code class="docutils literal notranslate"><span class="pre">func</span></code> with respect to the arg(s) at index
 <code class="docutils literal notranslate"><span class="pre">argnum</span></code> via a forward-over-reverse strategy.</p>
 <p>The forward-over-reverse strategy (composing <code class="docutils literal notranslate"><span class="pre">jacfwd(jacrev(func))</span></code>) is
diff --git a/2.9/generated/torch.func.jacfwd.html b/2.9/generated/torch.func.jacfwd.html
index dfa6db4261a..755f2107798 100644
--- a/2.9/generated/torch.func.jacfwd.html
+++ b/2.9/generated/torch.func.jacfwd.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.jacfwd<a class="headerlink" href="#torch-func-jacfwd" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.jacfwd">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">jacfwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">randomness</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'error'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/eager_transforms.py#L1139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.jacfwd" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">jacfwd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">randomness</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'error'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/eager_transforms.py#L1139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.jacfwd" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the Jacobian of <code class="docutils literal notranslate"><span class="pre">func</span></code> with respect to the arg(s) at index
 <code class="docutils literal notranslate"><span class="pre">argnum</span></code> using forward-mode autodiff</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.func.jacrev.html b/2.9/generated/torch.func.jacrev.html
index 98f946a2b78..e001a0a0710 100644
--- a/2.9/generated/torch.func.jacrev.html
+++ b/2.9/generated/torch.func.jacrev.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.jacrev<a class="headerlink" href="#torch-func-jacrev" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.jacrev">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">jacrev</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_preallocate_and_copy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/eager_transforms.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.jacrev" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">jacrev</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">argnums</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_preallocate_and_copy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/eager_transforms.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.jacrev" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the Jacobian of <code class="docutils literal notranslate"><span class="pre">func</span></code> with respect to the arg(s) at index
 <code class="docutils literal notranslate"><span class="pre">argnum</span></code> using reverse mode autodiff</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.func.jvp.html b/2.9/generated/torch.func.jvp.html
index 28a9a626ed8..654a39313d8 100644
--- a/2.9/generated/torch.func.jvp.html
+++ b/2.9/generated/torch.func.jvp.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.jvp<a class="headerlink" href="#torch-func-jvp" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.jvp">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">primals</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tangents</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/eager_transforms.py#L983"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.jvp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">jvp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">primals</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tangents</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/eager_transforms.py#L983"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.jvp" title="Permalink to this definition">#</a></dt>
 <dd><p>Standing for the Jacobian-vector product, returns a tuple containing
 the output of <cite>func(*primals)</cite> and the “Jacobian of <code class="docutils literal notranslate"><span class="pre">func</span></code> evaluated at
 <code class="docutils literal notranslate"><span class="pre">primals</span></code>” times <code class="docutils literal notranslate"><span class="pre">tangents</span></code>. This is also known as forward-mode autodiff.</p>
diff --git a/2.9/generated/torch.func.linearize.html b/2.9/generated/torch.func.linearize.html
index 8d6a4e1aa1e..0f59daa7723 100644
--- a/2.9/generated/torch.func.linearize.html
+++ b/2.9/generated/torch.func.linearize.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.linearize<a class="headerlink" href="#torch-func-linearize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.linearize">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">linearize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">primals</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/eager_transforms.py#L1678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.linearize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">linearize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">primals</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/eager_transforms.py#L1678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.linearize" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the value of <code class="docutils literal notranslate"><span class="pre">func</span></code> at <code class="docutils literal notranslate"><span class="pre">primals</span></code> and linear approximation
 at <code class="docutils literal notranslate"><span class="pre">primals</span></code>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.func.replace_all_batch_norm_modules_.html b/2.9/generated/torch.func.replace_all_batch_norm_modules_.html
index 4ea5b1ed9e6..7c5b0417760 100644
--- a/2.9/generated/torch.func.replace_all_batch_norm_modules_.html
+++ b/2.9/generated/torch.func.replace_all_batch_norm_modules_.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.replace_all_batch_norm_modules_<a class="headerlink" href="#torch-func-replace-all-batch-norm-modules" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.replace_all_batch_norm_modules_">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">replace_all_batch_norm_modules_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/batch_norm_replacement.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.replace_all_batch_norm_modules_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">replace_all_batch_norm_modules_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">root</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/batch_norm_replacement.py#L16"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.replace_all_batch_norm_modules_" title="Permalink to this definition">#</a></dt>
 <dd><p>In place updates <code class="xref py py-attr docutils literal notranslate"><span class="pre">root</span></code> by setting the <code class="docutils literal notranslate"><span class="pre">running_mean</span></code> and <code class="docutils literal notranslate"><span class="pre">running_var</span></code> to be None and
 setting track_running_stats to be False for any nn.BatchNorm module in <code class="xref py py-attr docutils literal notranslate"><span class="pre">root</span></code></p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.func.stack_module_state.html b/2.9/generated/torch.func.stack_module_state.html
index dd77aab7a63..5522743e1cc 100644
--- a/2.9/generated/torch.func.stack_module_state.html
+++ b/2.9/generated/torch.func.stack_module_state.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.stack_module_state<a class="headerlink" href="#torch-func-stack-module-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.stack_module_state">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">stack_module_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">models</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">params</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">buffers</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/functional_call.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.stack_module_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">stack_module_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">models</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">params</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">buffers</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/functional_call.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.stack_module_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Prepares a list of torch.nn.Modules for ensembling with <a class="reference internal" href="torch.func.vmap.html#torch.func.vmap" title="torch.func.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">vmap()</span></code></a>.</p>
 <p>Given a list of <code class="docutils literal notranslate"><span class="pre">M</span></code> <code class="docutils literal notranslate"><span class="pre">nn.Modules</span></code> of the same class, returns two dictionaries
 that stack all of their parameters and buffers together, indexed by name.
diff --git a/2.9/generated/torch.func.vjp.html b/2.9/generated/torch.func.vjp.html
index 79b057fe2b9..281ebbb1ddd 100644
--- a/2.9/generated/torch.func.vjp.html
+++ b/2.9/generated/torch.func.vjp.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.vjp<a class="headerlink" href="#torch-func-vjp" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.vjp">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">vjp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">primals</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/eager_transforms.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.vjp" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">vjp</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">primals</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/eager_transforms.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.vjp" title="Permalink to this definition">#</a></dt>
 <dd><p>Standing for the vector-Jacobian product, returns a tuple containing the
 results of <code class="docutils literal notranslate"><span class="pre">func</span></code> applied to <code class="docutils literal notranslate"><span class="pre">primals</span></code> and a function that, when
 given <code class="docutils literal notranslate"><span class="pre">cotangents</span></code>, computes the reverse-mode Jacobian of <code class="docutils literal notranslate"><span class="pre">func</span></code> with
diff --git a/2.9/generated/torch.func.vmap.html b/2.9/generated/torch.func.vmap.html
index 01ce96ca5f4..39660919905 100644
--- a/2.9/generated/torch.func.vmap.html
+++ b/2.9/generated/torch.func.vmap.html
@@ -4415,7 +4415,7 @@
 <h1>torch.func.vmap<a class="headerlink" href="#torch-func-vmap" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.func.vmap">
-<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">randomness</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'error'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/apis.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.vmap" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.func.</span></span><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">randomness</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'error'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/apis.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.func.vmap" title="Permalink to this definition">#</a></dt>
 <dd><p>vmap is the vectorizing map; <code class="docutils literal notranslate"><span class="pre">vmap(func)</span></code> returns a new function that
 maps <code class="docutils literal notranslate"><span class="pre">func</span></code> over some dimension of the inputs. Semantically, vmap
 pushes the map into PyTorch operations called by <code class="docutils literal notranslate"><span class="pre">func</span></code>, effectively
diff --git a/2.9/generated/torch.functional.align_tensors.html b/2.9/generated/torch.functional.align_tensors.html
index 38c94357481..20f57bb6b6b 100644
--- a/2.9/generated/torch.functional.align_tensors.html
+++ b/2.9/generated/torch.functional.align_tensors.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.align_tensors<a class="headerlink" href="#torch-functional-align-tensors" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.align_tensors">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">align_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L2194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.align_tensors" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">align_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L2194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.align_tensors" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
diff --git a/2.9/generated/torch.functional.atleast_1d.html b/2.9/generated/torch.functional.atleast_1d.html
index 140bc3208b5..ed9deead29a 100644
--- a/2.9/generated/torch.functional.atleast_1d.html
+++ b/2.9/generated/torch.functional.atleast_1d.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.atleast_1d<a class="headerlink" href="#torch-functional-atleast-1d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.atleast_1d">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">atleast_1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.atleast_1d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">atleast_1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.atleast_1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a 1-dimensional view of each input tensor with zero dimensions.
 Input tensors with one or more dimensions are returned as-is.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.functional.atleast_2d.html b/2.9/generated/torch.functional.atleast_2d.html
index 13663174786..4affc069d7d 100644
--- a/2.9/generated/torch.functional.atleast_2d.html
+++ b/2.9/generated/torch.functional.atleast_2d.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.atleast_2d<a class="headerlink" href="#torch-functional-atleast-2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.atleast_2d">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">atleast_2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.atleast_2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">atleast_2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.atleast_2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a 2-dimensional view of each input tensor with zero dimensions.
 Input tensors with two or more dimensions are returned as-is.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.functional.atleast_3d.html b/2.9/generated/torch.functional.atleast_3d.html
index 2e7412435c6..164d7adc17b 100644
--- a/2.9/generated/torch.functional.atleast_3d.html
+++ b/2.9/generated/torch.functional.atleast_3d.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.atleast_3d<a class="headerlink" href="#torch-functional-atleast-3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.atleast_3d">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">atleast_3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1548"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.atleast_3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">atleast_3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1548"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.atleast_3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a 3-dimensional view of each input tensor with zero dimensions.
 Input tensors with three or more dimensions are returned as-is.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.functional.block_diag.html b/2.9/generated/torch.functional.block_diag.html
index f491a475d77..907f91b6258 100644
--- a/2.9/generated/torch.functional.block_diag.html
+++ b/2.9/generated/torch.functional.block_diag.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.block_diag<a class="headerlink" href="#torch-functional-block-diag" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.block_diag">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">block_diag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.block_diag" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">block_diag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.block_diag" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a block diagonal matrix from provided tensors.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.functional.broadcast_shapes.html b/2.9/generated/torch.functional.broadcast_shapes.html
index 4c064911b8e..6538994d04b 100644
--- a/2.9/generated/torch.functional.broadcast_shapes.html
+++ b/2.9/generated/torch.functional.broadcast_shapes.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.broadcast_shapes<a class="headerlink" href="#torch-functional-broadcast-shapes" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.broadcast_shapes">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">broadcast_shapes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">shapes</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../size.html#torch.Size" title="torch.Size"><span class="pre">Size</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.broadcast_shapes" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">broadcast_shapes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">shapes</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../size.html#torch.Size" title="torch.Size"><span class="pre">Size</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.broadcast_shapes" title="Permalink to this definition">#</a></dt>
 <dd><p>Similar to <a class="reference internal" href="torch.functional.broadcast_tensors.html#torch.functional.broadcast_tensors" title="torch.functional.broadcast_tensors"><code class="xref py py-func docutils literal notranslate"><span class="pre">broadcast_tensors()</span></code></a> but for shapes.</p>
 <p>This is equivalent to
 <code class="docutils literal notranslate"><span class="pre">torch.broadcast_tensors(*map(torch.empty,</span> <span class="pre">shapes))[0].shape</span></code>
diff --git a/2.9/generated/torch.functional.broadcast_tensors.html b/2.9/generated/torch.functional.broadcast_tensors.html
index 469aafc9247..c4116606c71 100644
--- a/2.9/generated/torch.functional.broadcast_tensors.html
+++ b/2.9/generated/torch.functional.broadcast_tensors.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.broadcast_tensors<a class="headerlink" href="#torch-functional-broadcast-tensors" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.broadcast_tensors">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">broadcast_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">List</span> <span class="pre">of</span> <span class="pre">Tensors</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.broadcast_tensors" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">broadcast_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">List</span> <span class="pre">of</span> <span class="pre">Tensors</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.broadcast_tensors" title="Permalink to this definition">#</a></dt>
 <dd><p>Broadcasts the given tensors according to <a class="reference internal" href="../notes/broadcasting.html#broadcasting-semantics"><span class="std std-ref">Broadcasting semantics</span></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.functional.cartesian_prod.html b/2.9/generated/torch.functional.cartesian_prod.html
index f9bbf319fb3..2243acc9873 100644
--- a/2.9/generated/torch.functional.cartesian_prod.html
+++ b/2.9/generated/torch.functional.cartesian_prod.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.cartesian_prod<a class="headerlink" href="#torch-functional-cartesian-prod" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.cartesian_prod">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">cartesian_prod</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.cartesian_prod" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">cartesian_prod</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.cartesian_prod" title="Permalink to this definition">#</a></dt>
 <dd><p>Do cartesian product of the given sequence of tensors. The behavior is similar to
 python’s <cite>itertools.product</cite>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.functional.cdist.html b/2.9/generated/torch.functional.cdist.html
index 92ce04c0907..2c92b327330 100644
--- a/2.9/generated/torch.functional.cdist.html
+++ b/2.9/generated/torch.functional.cdist.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.cdist<a class="headerlink" href="#torch-functional-cdist" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.cdist">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">cdist</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'use_mm_for_euclid_dist_if_necessary'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.cdist" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">cdist</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'use_mm_for_euclid_dist_if_necessary'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.cdist" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes batched the p-norm distance between each pair of the two collections of row vectors.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.functional.chain_matmul.html b/2.9/generated/torch.functional.chain_matmul.html
index ddd19b1523c..29d91b2258f 100644
--- a/2.9/generated/torch.functional.chain_matmul.html
+++ b/2.9/generated/torch.functional.chain_matmul.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.chain_matmul<a class="headerlink" href="#torch-functional-chain-matmul" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.chain_matmul">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">chain_matmul</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">matrices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1981"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.chain_matmul" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">chain_matmul</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">matrices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1981"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.chain_matmul" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the matrix product of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>N</mi></mrow><annotation encoding="application/x-tex">N</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span></span></span></span></span> 2-D tensors. This product is efficiently computed
 using the matrix chain order algorithm which selects the order in which incurs the lowest cost in terms
 of arithmetic operations (<a class="reference external" href="https://mitpress.mit.edu/books/introduction-algorithms-third-edition">[CLRS]</a>). Note that since this is a function to compute the product, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>N</mi></mrow><annotation encoding="application/x-tex">N</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span></span></span></span></span>
diff --git a/2.9/generated/torch.functional.einsum.html b/2.9/generated/torch.functional.einsum.html
index 6be47f94f9e..78a38169ab2 100644
--- a/2.9/generated/torch.functional.einsum.html
+++ b/2.9/generated/torch.functional.einsum.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.einsum<a class="headerlink" href="#torch-functional-einsum" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.einsum">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">einsum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">equation</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">operands</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.einsum" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">einsum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">equation</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">operands</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.einsum" title="Permalink to this definition">#</a></dt>
 <dd><p>Sums the product of the elements of the input <code class="xref py py-attr docutils literal notranslate"><span class="pre">operands</span></code> along dimensions specified using a notation
 based on the Einstein summation convention.</p>
 <p>Einsum allows computing many common multi-dimensional linear algebraic array operations by representing them
diff --git a/2.9/generated/torch.functional.lu.html b/2.9/generated/torch.functional.lu.html
index a2cf06b7f39..c7c901bd839 100644
--- a/2.9/generated/torch.functional.lu.html
+++ b/2.9/generated/torch.functional.lu.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.lu<a class="headerlink" href="#torch-functional-lu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.lu">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">lu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.lu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">lu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.lu" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the LU factorization of a matrix or batches of matrices
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">A</span></code>. Returns a tuple containing the LU factorization and
 pivots of <code class="xref py py-attr docutils literal notranslate"><span class="pre">A</span></code>.  Pivoting is done if <code class="xref py py-attr docutils literal notranslate"><span class="pre">pivot</span></code> is set to
diff --git a/2.9/generated/torch.functional.meshgrid.html b/2.9/generated/torch.functional.meshgrid.html
index 5a8442d3fa3..e29b3e84187 100644
--- a/2.9/generated/torch.functional.meshgrid.html
+++ b/2.9/generated/torch.functional.meshgrid.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.meshgrid<a class="headerlink" href="#torch-functional-meshgrid" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.meshgrid">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">meshgrid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indexing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L396"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.meshgrid" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">meshgrid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indexing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L396"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.meshgrid" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates grids of coordinates specified by the 1D inputs in <cite>attr</cite>:tensors.</p>
 <p>This is helpful when you want to visualize data over some
 range of inputs. See below for a plotting example.</p>
diff --git a/2.9/generated/torch.functional.norm.html b/2.9/generated/torch.functional.norm.html
index 4442880d0b6..eb3061ec738 100644
--- a/2.9/generated/torch.functional.norm.html
+++ b/2.9/generated/torch.functional.norm.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.norm<a class="headerlink" href="#torch-functional-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.norm">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fro'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fro'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the matrix norm or vector norm of a given tensor.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.functional.split.html b/2.9/generated/torch.functional.split.html
index 6d2998eb85e..a23a65bcd72 100644
--- a/2.9/generated/torch.functional.split.html
+++ b/2.9/generated/torch.functional.split.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.split<a class="headerlink" href="#torch-functional-split" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.split">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_size_or_sections</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.split" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_size_or_sections</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.split" title="Permalink to this definition">#</a></dt>
 <dd><p>Splits the tensor into chunks. Each chunk is a view of the original tensor.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">split_size_or_sections</span></code> is an integer type, then <code class="xref py py-attr docutils literal notranslate"><span class="pre">tensor</span></code> will
 be split into equally sized chunks (if possible). Last chunk will be smaller if
diff --git a/2.9/generated/torch.functional.stft.html b/2.9/generated/torch.functional.stft.html
index 097c81d1e48..db138e72fc8 100644
--- a/2.9/generated/torch.functional.stft.html
+++ b/2.9/generated/torch.functional.stft.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.stft<a class="headerlink" href="#torch-functional-stft" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.stft">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">stft</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_fft</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">win_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reflect'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onesided</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_to_window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.stft" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">stft</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_fft</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">win_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reflect'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onesided</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_to_window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.stft" title="Permalink to this definition">#</a></dt>
 <dd><p>Short-time Fourier transform (STFT).</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.functional.tensordot.html b/2.9/generated/torch.functional.tensordot.html
index 7b020fab283..3e8c79d3960 100644
--- a/2.9/generated/torch.functional.tensordot.html
+++ b/2.9/generated/torch.functional.tensordot.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.tensordot<a class="headerlink" href="#torch-functional-tensordot" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.tensordot">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">tensordot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.tensordot" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">tensordot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.tensordot" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a contraction of a and b over multiple dimensions.</p>
 <p><a class="reference internal" href="#torch.functional.tensordot" title="torch.functional.tensordot"><code class="xref py py-attr docutils literal notranslate"><span class="pre">tensordot</span></code></a> implements a generalized matrix product.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.functional.unique.html b/2.9/generated/torch.functional.unique.html
index 20e2aae96d4..78ff1bbdade 100644
--- a/2.9/generated/torch.functional.unique.html
+++ b/2.9/generated/torch.functional.unique.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.unique<a class="headerlink" href="#torch-functional-unique" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.unique">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">unique</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_inverse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_counts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.unique" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">unique</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_inverse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_counts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.unique" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the unique elements of the input tensor.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.functional.unique_consecutive.html b/2.9/generated/torch.functional.unique_consecutive.html
index 17dd1673936..5d9190a8e04 100644
--- a/2.9/generated/torch.functional.unique_consecutive.html
+++ b/2.9/generated/torch.functional.unique_consecutive.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.unique_consecutive<a class="headerlink" href="#torch-functional-unique-consecutive" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.unique_consecutive">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">unique_consecutive</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.unique_consecutive" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">unique_consecutive</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.unique_consecutive" title="Permalink to this definition">#</a></dt>
 <dd><p>Eliminates all but the first element from every consecutive group of equivalent elements.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.functional.unravel_index.html b/2.9/generated/torch.functional.unravel_index.html
index a736f311a44..6306aefe25f 100644
--- a/2.9/generated/torch.functional.unravel_index.html
+++ b/2.9/generated/torch.functional.unravel_index.html
@@ -4415,7 +4415,7 @@
 <h1>torch.functional.unravel_index<a class="headerlink" href="#torch-functional-unravel-index" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.functional.unravel_index">
-<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">unravel_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1881"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.unravel_index" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.functional.</span></span><span class="sig-name descname"><span class="pre">unravel_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1881"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.functional.unravel_index" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts a tensor of flat indices into a tuple of coordinate tensors that
 index into an arbitrary tensor of the specified shape.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.fx.experimental.proxy_tensor.get_proxy_mode.html b/2.9/generated/torch.fx.experimental.proxy_tensor.get_proxy_mode.html
index d2317a8c6d1..5cb3a6eedf5 100644
--- a/2.9/generated/torch.fx.experimental.proxy_tensor.get_proxy_mode.html
+++ b/2.9/generated/torch.fx.experimental.proxy_tensor.get_proxy_mode.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.proxy_tensor.get_proxy_mode<a class="headerlink" href="#torch-fx-experimental-proxy-tensor-get-proxy-mode" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.proxy_tensor.get_proxy_mode">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">get_proxy_mode</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/proxy_tensor.py#L2444"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.get_proxy_mode" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">get_proxy_mode</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/proxy_tensor.py#L2444"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.get_proxy_mode" title="Permalink to this definition">#</a></dt>
 <dd><p>Current the currently active proxy tracing mode, or None if
 we are not currently tracing.  This includes pre-dispatch proxy
 tracing.</p>
diff --git a/2.9/generated/torch.fx.experimental.proxy_tensor.handle_sym_dispatch.html b/2.9/generated/torch.fx.experimental.proxy_tensor.handle_sym_dispatch.html
index 1f5bc6cf28d..d7e64f70964 100644
--- a/2.9/generated/torch.fx.experimental.proxy_tensor.handle_sym_dispatch.html
+++ b/2.9/generated/torch.fx.experimental.proxy_tensor.handle_sym_dispatch.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.proxy_tensor.handle_sym_dispatch<a class="headerlink" href="#torch-fx-experimental-proxy-tensor-handle-sym-dispatch" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.proxy_tensor.handle_sym_dispatch">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">handle_sym_dispatch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/proxy_tensor.py#L2460"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.handle_sym_dispatch" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">handle_sym_dispatch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/proxy_tensor.py#L2460"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.handle_sym_dispatch" title="Permalink to this definition">#</a></dt>
 <dd><p>Call into the currently active proxy tracing mode to do a
 SymInt/SymFloat/SymBool dispatch trace on a function that operates on
 these arguments.</p>
diff --git a/2.9/generated/torch.fx.experimental.proxy_tensor.make_fx.html b/2.9/generated/torch.fx.experimental.proxy_tensor.make_fx.html
index d5195f5e3b3..5d18036ea70 100644
--- a/2.9/generated/torch.fx.experimental.proxy_tensor.make_fx.html
+++ b/2.9/generated/torch.fx.experimental.proxy_tensor.make_fx.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.proxy_tensor.make_fx<a class="headerlink" href="#torch-fx-experimental-proxy-tensor-make-fx" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.proxy_tensor.make_fx">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">make_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decomposition_table</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracing_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'real'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_allow_non_fake_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pre_dispatch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_module_stack</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_allow_fake_constant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_error_on_data_dependent_ops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_stack_traces</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/proxy_tensor.py#L2391"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.make_fx" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">make_fx</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decomposition_table</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracing_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'real'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_allow_non_fake_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pre_dispatch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_module_stack</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_allow_fake_constant</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_error_on_data_dependent_ops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_stack_traces</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/proxy_tensor.py#L2391"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.make_fx" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a function f, return a new function which when executed with valid
 arguments to f, returns an FX GraphModule representing the set of operations that
 were executed during the course of execution.</p>
diff --git a/2.9/generated/torch.fx.experimental.proxy_tensor.maybe_disable_thunkify.html b/2.9/generated/torch.fx.experimental.proxy_tensor.maybe_disable_thunkify.html
index 3793061772d..897ea207230 100644
--- a/2.9/generated/torch.fx.experimental.proxy_tensor.maybe_disable_thunkify.html
+++ b/2.9/generated/torch.fx.experimental.proxy_tensor.maybe_disable_thunkify.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.proxy_tensor.maybe_disable_thunkify<a class="headerlink" href="#torch-fx-experimental-proxy-tensor-maybe-disable-thunkify" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.proxy_tensor.maybe_disable_thunkify">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">maybe_disable_thunkify</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/proxy_tensor.py#L506"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.maybe_disable_thunkify" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">maybe_disable_thunkify</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/proxy_tensor.py#L506"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.maybe_disable_thunkify" title="Permalink to this definition">#</a></dt>
 <dd><p>Within a context, disable thunkification.  See <a class="reference internal" href="torch.fx.experimental.proxy_tensor.maybe_enable_thunkify.html#torch.fx.experimental.proxy_tensor.maybe_enable_thunkify" title="torch.fx.experimental.proxy_tensor.maybe_enable_thunkify"><code class="xref py py-func docutils literal notranslate"><span class="pre">maybe_enable_thunkify()</span></code></a>
 for more details.  This is helpful if you have a wrapper function which
 you want to enable thunkification on, but in some segment on the inside (say,
diff --git a/2.9/generated/torch.fx.experimental.proxy_tensor.maybe_enable_thunkify.html b/2.9/generated/torch.fx.experimental.proxy_tensor.maybe_enable_thunkify.html
index 69c34c1a3fd..556e6cd680d 100644
--- a/2.9/generated/torch.fx.experimental.proxy_tensor.maybe_enable_thunkify.html
+++ b/2.9/generated/torch.fx.experimental.proxy_tensor.maybe_enable_thunkify.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.proxy_tensor.maybe_enable_thunkify<a class="headerlink" href="#torch-fx-experimental-proxy-tensor-maybe-enable-thunkify" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.proxy_tensor.maybe_enable_thunkify">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">maybe_enable_thunkify</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/proxy_tensor.py#L522"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.maybe_enable_thunkify" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.proxy_tensor.</span></span><span class="sig-name descname"><span class="pre">maybe_enable_thunkify</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/proxy_tensor.py#L522"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.proxy_tensor.maybe_enable_thunkify" title="Permalink to this definition">#</a></dt>
 <dd><p>Within this context manager, if you are doing make_fx tracing, we will thunkify
 all SymNode compute and avoid tracing it into the graph unless it is actually needed.
 You should prefer to avoid using this as much as possible, as lazy evaluation of
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.CallMethodKey.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.CallMethodKey.html
index c2e21256c16..91f9721f1e2 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.CallMethodKey.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.CallMethodKey.html
@@ -4404,12 +4404,12 @@
 <h1>CallMethodKey<a class="headerlink" href="#callmethodkey" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.CallMethodKey">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">CallMethodKey</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'str'</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1047"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.CallMethodKey" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">CallMethodKey</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'str'</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1047"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.CallMethodKey" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.CallMethodKey.get">
-<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">o</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1054"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.CallMethodKey.get" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">o</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1054"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.CallMethodKey.get" title="Permalink to this definition">#</a></dt>
 <dd><p>Call the method on object</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.ConvertIntKey.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.ConvertIntKey.html
index 0a00a47746f..654287d84ba 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.ConvertIntKey.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.ConvertIntKey.html
@@ -4404,12 +4404,12 @@
 <h1>ConvertIntKey<a class="headerlink" href="#convertintkey" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ConvertIntKey">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">ConvertIntKey</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1037"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ConvertIntKey" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">ConvertIntKey</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1037"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ConvertIntKey" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ConvertIntKey.get">
-<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1042"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ConvertIntKey.get" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1042"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ConvertIntKey.get" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the int value from bool</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.DimConstraints.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.DimConstraints.html
index 83d32af6676..7da3e52a0e8 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.DimConstraints.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.DimConstraints.html
@@ -4404,14 +4404,14 @@
 <h1>DimConstraints<a class="headerlink" href="#dimconstraints" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DimConstraints">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">DimConstraints</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbol_to_source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">var_to_val</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">marked_dynamic</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source_name_to_debug_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L2791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">DimConstraints</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbol_to_source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">var_to_val</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">marked_dynamic</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source_name_to_debug_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L2791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints" title="Permalink to this definition">#</a></dt>
 <dd><p>Custom solver for a system of constraints on symbolic dimensions.
 Solutions are “static” values or simplified “dynamic” constraints.</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DimConstraints.add">
-<span class="sig-name descname"><span class="pre">add</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L2951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.add" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L2951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.add" title="Permalink to this definition">#</a></dt>
 <dd><p>Add an expression to the set of constraints.</p>
 <p>Return whether the expression is a trivial constraint (i.e., an obvious tautology).</p>
 <dl class="field-list simple">
@@ -4423,7 +4423,7 @@ <h1>DimConstraints<a class="headerlink" href="#dimconstraints" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DimConstraints.add_equality">
-<span class="sig-name descname"><span class="pre">add_equality</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L2998"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.add_equality" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_equality</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L2998"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.add_equality" title="Permalink to this definition">#</a></dt>
 <dd><p>Add an equality constraint</p>
 <dl class="field-list simple">
 </dl>
@@ -4431,7 +4431,7 @@ <h1>DimConstraints<a class="headerlink" href="#dimconstraints" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DimConstraints.forced_specializations">
-<span class="sig-name descname"><span class="pre">forced_specializations</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L3169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.forced_specializations" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forced_specializations</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L3169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.forced_specializations" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a dictionary of the names of symbols to their specialized value</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4442,7 +4442,7 @@ <h1>DimConstraints<a class="headerlink" href="#dimconstraints" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DimConstraints.prettify_results">
-<span class="sig-name descname"><span class="pre">prettify_results</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">original_signature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_violation_error</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forced_specializations</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L3377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.prettify_results" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prettify_results</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">original_signature</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_violation_error</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forced_specializations</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L3377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.prettify_results" title="Permalink to this definition">#</a></dt>
 <dd><p>Format a message for constraint violation errors</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4453,7 +4453,7 @@ <h1>DimConstraints<a class="headerlink" href="#dimconstraints" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DimConstraints.rewrite_with_congruences">
-<span class="sig-name descname"><span class="pre">rewrite_with_congruences</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">s</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L2858"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.rewrite_with_congruences" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rewrite_with_congruences</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">s</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L2858"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.rewrite_with_congruences" title="Permalink to this definition">#</a></dt>
 <dd><p>Eliminate expressions of the form b // d and b % d while adding congruences of the form b % d == k.
 This leaves rational operators (in particular of the form b / d) that our inequality solver can handle.
 We solve the added congruences separately (using our congruence solver, see below).</p>
@@ -4466,7 +4466,7 @@ <h1>DimConstraints<a class="headerlink" href="#dimconstraints" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DimConstraints.solve">
-<span class="sig-name descname"><span class="pre">solve</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L3061"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.solve" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">solve</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L3061"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimConstraints.solve" title="Permalink to this definition">#</a></dt>
 <dd><p>Solve the system of constraint equations to find simplified constraints</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.DimDynamic.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.DimDynamic.html
index 0cc13becad1..472a1dff1f3 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.DimDynamic.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.DimDynamic.html
@@ -4404,7 +4404,7 @@
 <h1>DimDynamic<a class="headerlink" href="#dimdynamic" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DimDynamic">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">DimDynamic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1762"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimDynamic" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">DimDynamic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1762"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DimDynamic" title="Permalink to this definition">#</a></dt>
 <dd><p>Controls how to perform symbol allocation for a dimension.  It is always
 sound to default this to DYNAMIC, but the policies DUCK and STATIC can
 result in better trace-time and compile-time performance, as they reduce
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.DivideByKey.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.DivideByKey.html
index 59fecd6af6f..d4f7f5f402f 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.DivideByKey.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.DivideByKey.html
@@ -4404,12 +4404,12 @@
 <h1>DivideByKey<a class="headerlink" href="#dividebykey" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DivideByKey">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">DivideByKey</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">divisor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'IntLikeType'</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1071"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DivideByKey" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">DivideByKey</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">divisor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'IntLikeType'</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1071"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DivideByKey" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.DivideByKey.get">
-<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">o</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1078"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DivideByKey.get" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">o</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1078"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.DivideByKey.get" title="Permalink to this definition">#</a></dt>
 <dd><p>Divide object by divisor</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.EqualityConstraint.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.EqualityConstraint.html
index 9591cb1ff7f..3b46e71b1dd 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.EqualityConstraint.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.EqualityConstraint.html
@@ -4404,7 +4404,7 @@
 <h1>EqualityConstraint<a class="headerlink" href="#equalityconstraint" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.EqualityConstraint">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">EqualityConstraint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">warn_only</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source_pairs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">derived_equalities</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">phantom_symbols</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relaxed_sources</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.EqualityConstraint" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">EqualityConstraint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">warn_only</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source_pairs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">derived_equalities</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">phantom_symbols</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relaxed_sources</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.EqualityConstraint" title="Permalink to this definition">#</a></dt>
 <dd><p>Represent and decide various kinds of equality constraints between input sources.</p>
 <p>A “source pair” is a pair of input sources for dynamic dimensions that
 are specified equal. We represent <cite>source_pairs</cite> in a union-find forest
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.InnerTensorKey.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.InnerTensorKey.html
index ed1819f3d0c..0e58128213a 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.InnerTensorKey.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.InnerTensorKey.html
@@ -4404,12 +4404,12 @@
 <h1>InnerTensorKey<a class="headerlink" href="#innertensorkey" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.InnerTensorKey">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">InnerTensorKey</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inner_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'str'</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1059"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.InnerTensorKey" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">InnerTensorKey</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inner_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="s"><span class="pre">'str'</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1059"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.InnerTensorKey" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.InnerTensorKey.get">
-<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">o</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1066"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.InnerTensorKey.get" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">o</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1066"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.InnerTensorKey.get" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the inner tensor attribute</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.html
index 8f7b792d405..1cb773053a6 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.html
@@ -4404,12 +4404,12 @@
 <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymints" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">PropagateUnbackedSymInts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">garbage_collect_values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L7857"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">PropagateUnbackedSymInts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">garbage_collect_values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L7857"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.boxed_run">
-<span class="sig-name descname"><span class="pre">boxed_run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args_list</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.boxed_run" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">boxed_run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args_list</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.boxed_run" title="Permalink to this definition">#</a></dt>
 <dd><p>Run <cite>module</cite> via interpretation and return the result.  This uses the “boxed”
 calling convention, where you pass a list of arguments, which will be cleared
 by the interpreter.  This ensures that input tensors are promptly deallocated.</p>
@@ -4421,7 +4421,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_function">
-<span class="sig-name descname"><span class="pre">call_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_function" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_function" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">call_function</span></code> node and return the result.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4449,7 +4449,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_method">
-<span class="sig-name descname"><span class="pre">call_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_method" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_method" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">call_method</span></code> node and return the result.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4477,7 +4477,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_module">
-<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.call_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">call_module</span></code> node and return the result.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4505,7 +4505,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.fetch_args_kwargs_from_env">
-<span class="sig-name descname"><span class="pre">fetch_args_kwargs_from_env</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.fetch_args_kwargs_from_env" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fetch_args_kwargs_from_env</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.fetch_args_kwargs_from_env" title="Permalink to this definition">#</a></dt>
 <dd><p>Fetch the concrete values of <code class="docutils literal notranslate"><span class="pre">args</span></code> and <code class="docutils literal notranslate"><span class="pre">kwargs</span></code> of node <code class="docutils literal notranslate"><span class="pre">n</span></code>
 from the current execution environment.</p>
 <dl class="field-list simple">
@@ -4527,7 +4527,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.fetch_attr">
-<span class="sig-name descname"><span class="pre">fetch_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.fetch_attr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fetch_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.fetch_attr" title="Permalink to this definition">#</a></dt>
 <dd><p>Fetch an attribute from the <code class="docutils literal notranslate"><span class="pre">Module</span></code> hierarchy of <code class="docutils literal notranslate"><span class="pre">self.module</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4548,7 +4548,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.get_attr">
-<span class="sig-name descname"><span class="pre">get_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.get_attr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_attr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L295"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.get_attr" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">get_attr</span></code> node. Will retrieve an attribute
 value from the <code class="docutils literal notranslate"><span class="pre">Module</span></code> hierarchy of <code class="docutils literal notranslate"><span class="pre">self.module</span></code>.</p>
 <dl class="field-list simple">
@@ -4576,7 +4576,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.map_nodes_to_values">
-<span class="sig-name descname"><span class="pre">map_nodes_to_values</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L447"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.map_nodes_to_values" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">map_nodes_to_values</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L447"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.map_nodes_to_values" title="Permalink to this definition">#</a></dt>
 <dd><p>Recursively descend through <code class="docutils literal notranslate"><span class="pre">args</span></code> and look up the concrete value
 for each <code class="docutils literal notranslate"><span class="pre">Node</span></code> in the current execution environment.</p>
 <dl class="field-list simple">
@@ -4598,7 +4598,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.output">
-<span class="sig-name descname"><span class="pre">output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L387"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.output" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L387"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.output" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute an <code class="docutils literal notranslate"><span class="pre">output</span></code> node. This really just retrieves
 the value referenced by the <code class="docutils literal notranslate"><span class="pre">output</span></code> node and returns it.</p>
 <dl class="field-list simple">
@@ -4626,7 +4626,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.placeholder">
-<span class="sig-name descname"><span class="pre">placeholder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.placeholder" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">placeholder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.placeholder" title="Permalink to this definition">#</a></dt>
 <dd><p>Execute a <code class="docutils literal notranslate"><span class="pre">placeholder</span></code> node. Note that this is stateful:
 <code class="docutils literal notranslate"><span class="pre">Interpreter</span></code> maintains an internal iterator over
 arguments passed to <code class="docutils literal notranslate"><span class="pre">run</span></code> and this method returns
@@ -4656,7 +4656,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.run">
-<span class="sig-name descname"><span class="pre">run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">initial_env</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_io_processing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/interpreter.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.run" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">initial_env</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_io_processing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/interpreter.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.run" title="Permalink to this definition">#</a></dt>
 <dd><p>Run <cite>module</cite> via interpretation and return the result.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4685,7 +4685,7 @@ <h1>PropagateUnbackedSymInts<a class="headerlink" href="#propagateunbackedsymint
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.run_node">
-<span class="sig-name descname"><span class="pre">run_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L7858"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.run_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">run_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L7858"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.PropagateUnbackedSymInts.run_node" title="Permalink to this definition">#</a></dt>
 <dd><p>Run an FX node, propagating unbacked Symbol bindings to the new fake tensor</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.RelaxedUnspecConstraint.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.RelaxedUnspecConstraint.html
index 8bc1d81c82a..f3c7ec2d488 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.RelaxedUnspecConstraint.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.RelaxedUnspecConstraint.html
@@ -4404,7 +4404,7 @@
 <h1>RelaxedUnspecConstraint<a class="headerlink" href="#relaxedunspecconstraint" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.RelaxedUnspecConstraint">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">RelaxedUnspecConstraint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">warn_only</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1849"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.RelaxedUnspecConstraint" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">RelaxedUnspecConstraint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">warn_only</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1849"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.RelaxedUnspecConstraint" title="Permalink to this definition">#</a></dt>
 <dd><p>For clients: no explicit constraint; constraint is whatever is implicitly
 inferred by guards from tracing.</p>
 <p>For backends: there must exist at least TWO possible values for the
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.ShapeEnv.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.ShapeEnv.html
index 4ee002e9c8f..796bc0cf988 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.ShapeEnv.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.ShapeEnv.html
@@ -4404,12 +4404,12 @@
 <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">ShapeEnv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">should_record_events</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracked_fakes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L3562"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">ShapeEnv</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">should_record_events</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracked_fakes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L3562"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.add_var_to_val">
-<span class="sig-name descname"><span class="pre">add_var_to_val</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L5167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.add_var_to_val" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_var_to_val</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L5167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.add_var_to_val" title="Permalink to this definition">#</a></dt>
 <dd><p>Adds a new symbol to the symbolic environment.</p>
 <dl class="field-list simple">
 </dl>
@@ -4417,7 +4417,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.bind_symbols">
-<span class="sig-name descname"><span class="pre">bind_symbols</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholders</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6065"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.bind_symbols" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bind_symbols</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholders</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6065"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.bind_symbols" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a paired list of placeholders (fake tensors with
 symbolic sizes) and concrete arguments (regular tensors
 with real sizes), returns a dictionary mapping each
@@ -4440,7 +4440,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.bound_sympy">
-<span class="sig-name descname"><span class="pre">bound_sympy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_oblivious</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.bound_sympy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bound_sympy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_oblivious</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.bound_sympy" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a sympy expression, computes a ValueRanges bound for what values it can be</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4451,7 +4451,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.check_equal">
-<span class="sig-name descname"><span class="pre">check_equal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">other</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L3943"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.check_equal" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">check_equal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">other</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L3943"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.check_equal" title="Permalink to this definition">#</a></dt>
 <dd><p>Compare another ShapeEnv for equivalence</p>
 <dl class="field-list simple">
 </dl>
@@ -4459,7 +4459,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.cleanup">
-<span class="sig-name descname"><span class="pre">cleanup</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L7666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.cleanup" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cleanup</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L7666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.cleanup" title="Permalink to this definition">#</a></dt>
 <dd><p>Break reference cycles.</p>
 <p>This destroys the stacks. If you really want to keep them, we
 just need some way to break references on code objects.</p>
@@ -4469,7 +4469,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symbol">
-<span class="sig-name descname"><span class="pre">create_symbol</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">DimDynamic.DUCK</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">do_not_specialize_zero_one</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">symbolic_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symbol" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_symbol</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">DimDynamic.DUCK</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">do_not_specialize_zero_one</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">symbolic_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symbol" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a new symbol which is tracked by this ShapeEnv</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4480,7 +4480,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symbolic_sizes_strides_storage_offset">
-<span class="sig-name descname"><span class="pre">create_symbolic_sizes_strides_storage_offset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ex</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">symbolic_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4400"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symbolic_sizes_strides_storage_offset" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_symbolic_sizes_strides_storage_offset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ex</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">symbolic_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4400"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symbolic_sizes_strides_storage_offset" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a list of symbolic sizes and strides for the given tensor.
 We try our best to express stride in terms of the sizes, so as to not
 introduce new symbolic variables.</p>
@@ -4493,7 +4493,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symboolnode">
-<span class="sig-name descname"><span class="pre">create_symboolnode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sym</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4758"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symboolnode" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_symboolnode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sym</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4758"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symboolnode" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a SymBool object from a sympy boolean expression</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4504,7 +4504,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symfloatnode">
-<span class="sig-name descname"><span class="pre">create_symfloatnode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sym</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4706"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symfloatnode" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_symfloatnode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sym</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4706"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symfloatnode" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a SymFloat value from a symbolic expression</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4515,7 +4515,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symintnode">
-<span class="sig-name descname"><span class="pre">create_symintnode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sym</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4662"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symintnode" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_symintnode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sym</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hint</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4662"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_symintnode" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a SymInt value from a symbolic expression</p>
 <p>If you know what the current hint value of the SymInt to be created
 is, pass it into hint.  Otherwise, pass None and we will make our best
@@ -4529,7 +4529,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symbool">
-<span class="sig-name descname"><span class="pre">create_unbacked_symbool</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4855"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symbool" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_unbacked_symbool</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4855"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symbool" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a symbolic boolean without a hint value</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4540,7 +4540,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symfloat">
-<span class="sig-name descname"><span class="pre">create_unbacked_symfloat</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4801"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symfloat" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_unbacked_symfloat</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4801"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symfloat" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a symbolic float without a hint value</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4551,7 +4551,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symint">
-<span class="sig-name descname"><span class="pre">create_unbacked_symint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4826"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symint" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_unbacked_symint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4826"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unbacked_symint" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a symbolic integer without a hint value</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4562,7 +4562,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unspecified_symbol">
-<span class="sig-name descname"><span class="pre">create_unspecified_symbol</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">DimDynamic.DUCK</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">symbolic_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unspecified_symbol" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_unspecified_symbol</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">DimDynamic.DUCK</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">symbolic_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unspecified_symbol" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a symbol with an unspecified value</p>
 <p>Compared to standard symbols we do not assume the value is positive,
 nor do we specialze on zero or one values.</p>
@@ -4575,7 +4575,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unspecified_symint_and_symbol">
-<span class="sig-name descname"><span class="pre">create_unspecified_symint_and_symbol</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_dim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4743"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unspecified_symint_and_symbol" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">create_unspecified_symint_and_symbol</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_dim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4743"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.create_unspecified_symint_and_symbol" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a SymInt wrapping a new unspecified symbol</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4586,7 +4586,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.deserialize_symexpr">
-<span class="sig-name descname"><span class="pre">deserialize_symexpr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6021"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.deserialize_symexpr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">deserialize_symexpr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6021"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.deserialize_symexpr" title="Permalink to this definition">#</a></dt>
 <dd><p>To be used by compile_fx to deserialize symexprs</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4597,7 +4597,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_expr">
-<span class="sig-name descname"><span class="pre">evaluate_expr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">orig_expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hint</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fx_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_oblivious</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forcing_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L7316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_expr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">evaluate_expr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">orig_expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hint</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fx_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_oblivious</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">forcing_spec</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L7316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_expr" title="Permalink to this definition">#</a></dt>
 <dd><p>Given an expression, evaluates it, adding guards if necessary
 When fallback_value is not None the function return fallback_value instead of failing with data dependent error.</p>
 <dl class="field-list simple">
@@ -4609,7 +4609,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_guards_expression">
-<span class="sig-name descname"><span class="pre">evaluate_guards_expression</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6031"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_guards_expression" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">evaluate_guards_expression</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6031"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_guards_expression" title="Permalink to this definition">#</a></dt>
 <dd><p>Expected to be used with produce_guards_expression(). Evaluates an expression
 generated by produce_guards_expression for the given concrete args.</p>
 <dl class="field-list simple">
@@ -4621,7 +4621,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_guards_for_args">
-<span class="sig-name descname"><span class="pre">evaluate_guards_for_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholders</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_static</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6039"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_guards_for_args" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">evaluate_guards_for_args</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholders</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_static</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6039"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_guards_for_args" title="Permalink to this definition">#</a></dt>
 <dd><p>Generate guards for a graph’s placeholder values and evaluate the guards with args</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4632,7 +4632,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_sym_node">
-<span class="sig-name descname"><span class="pre">evaluate_sym_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sym_node</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_oblivious</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L7222"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_sym_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">evaluate_sym_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sym_node</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_oblivious</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L7222"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_sym_node" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a a SymNode, evaluates sym_node.expr, adding guards if necessary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4643,7 +4643,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_symexpr">
-<span class="sig-name descname"><span class="pre">evaluate_symexpr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6014"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_symexpr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">evaluate_symexpr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">code</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6014"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.evaluate_symexpr" title="Permalink to this definition">#</a></dt>
 <dd><p>To be used by compile_fx to evaluate symexprs</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4654,7 +4654,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.format_guards">
-<span class="sig-name descname"><span class="pre">format_guards</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.format_guards" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">format_guards</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.format_guards" title="Permalink to this definition">#</a></dt>
 <dd><p>Format this shape env’s guard expressions with optional traceback info if verbose</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4665,7 +4665,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.freeze">
-<span class="sig-name descname"><span class="pre">freeze</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.freeze" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">freeze</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.freeze" title="Permalink to this definition">#</a></dt>
 <dd><p>Freeze this ShapeEnv to stop accumulating guards</p>
 <p>A frozen ShapeEnv will ignore any further guards generated on it and
 only emit a warning which may lead to accuracy problems.</p>
@@ -4675,7 +4675,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.freeze_runtime_asserts">
-<span class="sig-name descname"><span class="pre">freeze_runtime_asserts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.freeze_runtime_asserts" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">freeze_runtime_asserts</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.freeze_runtime_asserts" title="Permalink to this definition">#</a></dt>
 <dd><p>Freeze this ShapeEnv to stop adding deferred runtime asserts.</p>
 <p>We will error if you try to install a new runtime assert when it is
 frozen.  This would indicate a lowering violation, or perhaps something
@@ -4687,7 +4687,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.get_axioms">
-<span class="sig-name descname"><span class="pre">get_axioms</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbols</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_hint</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.get_axioms" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_axioms</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbols</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_hint</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.get_axioms" title="Permalink to this definition">#</a></dt>
 <dd><p>Given the symbols in an expression, it returns all the runtime asserts that have those symbols
 concatenated with all the guards.
 If symbols is None, it returns all the runtime asserts (and all the guards)</p>
@@ -4700,7 +4700,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.get_implications">
-<span class="sig-name descname"><span class="pre">get_implications</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">e</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.get_implications" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_implications</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">e</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.get_implications" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a expression, it returns a list of predicates that follow from it</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4711,7 +4711,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.get_nontrivial_guards">
-<span class="sig-name descname"><span class="pre">get_nontrivial_guards</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.get_nontrivial_guards" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_nontrivial_guards</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.get_nontrivial_guards" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a list of guard expressions that aren’t statically known (i.e. not trivial)</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4722,7 +4722,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.get_pruned_guards">
-<span class="sig-name descname"><span class="pre">get_pruned_guards</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symints</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6052"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.get_pruned_guards" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_pruned_guards</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symints</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6052"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.get_pruned_guards" title="Permalink to this definition">#</a></dt>
 <dd><p>Get a list of guards, but pruned so it only provides guards that
 reference symints from the passed in input</p>
 <dl class="field-list simple">
@@ -4734,7 +4734,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.guard_or_defer_runtime_assert">
-<span class="sig-name descname"><span class="pre">guard_or_defer_runtime_assert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">orig_expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">msg</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fx_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L7679"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.guard_or_defer_runtime_assert" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">guard_or_defer_runtime_assert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">orig_expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">msg</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fx_node</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L7679"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.guard_or_defer_runtime_assert" title="Permalink to this definition">#</a></dt>
 <dd><p>Adds a guard that orig_expr is True if we can or fall back to adding an assert
 that is checked at runtime.</p>
 <dl class="field-list simple">
@@ -4754,7 +4754,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.ignore_fresh_unbacked_symbols">
-<span class="sig-name descname"><span class="pre">ignore_fresh_unbacked_symbols</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.ignore_fresh_unbacked_symbols" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">ignore_fresh_unbacked_symbols</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.ignore_fresh_unbacked_symbols" title="Permalink to this definition">#</a></dt>
 <dd><p>Indicates that the newly allocated unbacked SymInts are being
 discarded</p>
 <dl class="field-list simple">
@@ -4766,7 +4766,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.is_unbacked_symint">
-<span class="sig-name descname"><span class="pre">is_unbacked_symint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbol</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4851"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.is_unbacked_symint" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_unbacked_symint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbol</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4851"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.is_unbacked_symint" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if a sympy symbol matches the naming convention for unbacked symbols</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4777,7 +4777,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.patch_source_specialization">
-<span class="sig-name descname"><span class="pre">patch_source_specialization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L3897"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.patch_source_specialization" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">patch_source_specialization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L3897"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.patch_source_specialization" title="Permalink to this definition">#</a></dt>
 <dd><p>Temporarily add symbol-level axioms to the ShapeEnv. This is useful when you want to “fork”
 and have parallel universes of ShapeEnvs. For example, we use this when doing multi-graph
 compile so we can support various graphs with varying levels of specializations.</p>
@@ -4799,7 +4799,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards">
-<span class="sig-name descname"><span class="pre">produce_guards</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L5199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">produce_guards</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L5199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards" title="Permalink to this definition">#</a></dt>
 <dd><p>Like produce_guards_verbose, but only returns the non-verbose python guard expressions
 (no verbose guards produced.)</p>
 <dl class="field-list simple">
@@ -4811,7 +4811,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards_expression">
-<span class="sig-name descname"><span class="pre">produce_guards_expression</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholders</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_static</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L5989"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards_expression" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">produce_guards_expression</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholders</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">guards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_static</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L5989"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards_expression" title="Permalink to this definition">#</a></dt>
 <dd><p>Expected to be used with evaluate_guards_expression(). Produces the guards
 for the given placeholders and returns a string expression to be evaluated
 by evaluate_guards_expression given concrete values for the placeholders.</p>
@@ -4824,7 +4824,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards_verbose">
-<span class="sig-name descname"><span class="pre">produce_guards_verbose</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholders</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source_ref=&lt;function</span> <span class="pre">ShapeEnv.&lt;lambda&gt;&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">guards=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_contexts=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">equalities_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_simplified=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_static=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">langs=('python'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">'verbose_python')</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L5206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards_verbose" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">produce_guards_verbose</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">placeholders</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source_ref=&lt;function</span> <span class="pre">ShapeEnv.&lt;lambda&gt;&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">guards=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_contexts=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">equalities_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_simplified=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_static=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">langs=('python'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">'verbose_python')</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L5206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.produce_guards_verbose" title="Permalink to this definition">#</a></dt>
 <dd><p>Generates a list of guards strings which, when evaluated in a context that
 defines tensors for all the sources, returns True or False depending
 on if the guards in the list evaluated to True or not.  Primarily used by Dynamo,
@@ -4849,7 +4849,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.replace">
-<span class="sig-name descname"><span class="pre">replace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.replace" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">replace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.replace" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply symbol replacements to any symbols in the given expression.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4860,7 +4860,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.set_unbacked_var_to_val">
-<span class="sig-name descname"><span class="pre">set_unbacked_var_to_val</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">k</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4044"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.set_unbacked_var_to_val" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_unbacked_var_to_val</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">k</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">v</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4044"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.set_unbacked_var_to_val" title="Permalink to this definition">#</a></dt>
 <dd><p>Used only when propagate_real_tensors; registers a value for an
 unbacked symbol, which can be used last resort to resolve hints.</p>
 <dl class="field-list simple">
@@ -4869,7 +4869,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.simplify">
-<span class="sig-name descname"><span class="pre">simplify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_oblivious</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6343"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.simplify" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">simplify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_oblivious</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6343"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.simplify" title="Permalink to this definition">#</a></dt>
 <dd><p>Use known constraints and replacements to simplify the given expr</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4880,7 +4880,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.size_hint">
-<span class="sig-name descname"><span class="pre">size_hint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L6437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.size_hint" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">size_hint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L6437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.size_hint" title="Permalink to this definition">#</a></dt>
 <dd><p>Gets a size hint for a given expression from the underlying shapes we had.
 Does not introduce a guard, so only use this when you can guarantee that
 your code is still valid for arbitrary shapes (such as optimization decisions)</p>
@@ -4893,7 +4893,7 @@ <h1>ShapeEnv<a class="headerlink" href="#shapeenv" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnv.suppress_guards">
-<span class="sig-name descname"><span class="pre">suppress_guards</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L4307"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.suppress_guards" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">suppress_guards</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L4307"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnv.suppress_guards" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager to ignore all guards generated inside</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.ShapeEnvSettings.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.ShapeEnvSettings.html
index 597b35ded89..759124146d1 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.ShapeEnvSettings.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.ShapeEnvSettings.html
@@ -4404,7 +4404,7 @@
 <h1>ShapeEnvSettings<a class="headerlink" href="#shapeenvsettings" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.ShapeEnvSettings">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">ShapeEnvSettings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">allow_scalar_outputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_dynamic_output_shape_ops</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assume_static_by_default</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">specialize_zero_one</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">duck_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefer_deferred_runtime_asserts_over_guards</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trace_asserts</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L3520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnvSettings" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">ShapeEnvSettings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">allow_scalar_outputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_dynamic_output_shape_ops</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assume_static_by_default</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">specialize_zero_one</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">duck_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefer_deferred_runtime_asserts_over_guards</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trace_asserts</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L3520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.ShapeEnvSettings" title="Permalink to this definition">#</a></dt>
 <dd><p>Encapsulates all shape env settings that could potentially affect
 FakeTensor dispatch. Used when creating dispatch cache keys.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.Specialization.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.Specialization.html
index 6d91c176be8..6c5b5fd1f74 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.Specialization.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.Specialization.html
@@ -4404,7 +4404,7 @@
 <h1>Specialization<a class="headerlink" href="#specialization" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.Specialization">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">Specialization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1022"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.Specialization" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">Specialization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1022"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.Specialization" title="Permalink to this definition">#</a></dt>
 <dd><p>This class is used in multi-graph compilation contexts where we generate
 multiple specialized graphs and dispatch to the appropriate one at runtime.
 This allows us to optimize the trade-off between performance and generality
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.StatefulSymbolicContext.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.StatefulSymbolicContext.html
index edc9f9caede..0041831c9c1 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.StatefulSymbolicContext.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.StatefulSymbolicContext.html
@@ -4404,7 +4404,7 @@
 <h1>StatefulSymbolicContext<a class="headerlink" href="#statefulsymboliccontext" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.StatefulSymbolicContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">StatefulSymbolicContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dynamic_sizes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">specialize_on</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">view_base_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape_env_to_source_to_symbol_cache</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L2116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.StatefulSymbolicContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">StatefulSymbolicContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dynamic_sizes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">specialize_on</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">view_base_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape_env_to_source_to_symbol_cache</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L2116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.StatefulSymbolicContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Create symbols in <code class="docutils literal notranslate"><span class="pre">create_symbolic_sizes_strides_storage_offset</span></code> via
 a symbolic_context determination as given by a cache of Source:Symbol. A cache hit
 will reuse a stored symbol, and a cache miss will write to this cache.</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.StatelessSymbolicContext.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.StatelessSymbolicContext.html
index 7d084f748cc..a2fa39abf99 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.StatelessSymbolicContext.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.StatelessSymbolicContext.html
@@ -4404,7 +4404,7 @@
 <h1>StatelessSymbolicContext<a class="headerlink" href="#statelesssymboliccontext" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.StatelessSymbolicContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">StatelessSymbolicContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dynamic_sizes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">specialize_on</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">view_base_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L2048"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.StatelessSymbolicContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">StatelessSymbolicContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dynamic_sizes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">specialize_on</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">view_base_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L2048"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.StatelessSymbolicContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Create symbols in <code class="docutils literal notranslate"><span class="pre">create_symbolic_sizes_strides_storage_offset</span></code> via
 a symbolic_context determination as given by <code class="docutils literal notranslate"><span class="pre">DimDynamic</span></code> and <code class="docutils literal notranslate"><span class="pre">DimConstraint</span></code>.
 This will cause fresh symbols to be allocated</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint.html
index 88b76ff2ba8..1706df74d91 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint.html
@@ -4404,7 +4404,7 @@
 <h1>StrictMinMaxConstraint<a class="headerlink" href="#strictminmaxconstraint" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">StrictMinMaxConstraint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">warn_only</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1820"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">StrictMinMaxConstraint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">warn_only</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1820"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint" title="Permalink to this definition">#</a></dt>
 <dd><p>For clients: the size at this dimension must be within ‘vr’ (which
 specifies a lower and upper bound, inclusive-inclusive) AND it
 must be non-negative and should not be 0 or 1 (but see NB below).</p>
@@ -4422,7 +4422,7 @@ <h1>StrictMinMaxConstraint<a class="headerlink" href="#strictminmaxconstraint" t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint.render">
-<span class="sig-name descname"><span class="pre">render</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1843"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint.render" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">render</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1843"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.StrictMinMaxConstraint.render" title="Permalink to this definition">#</a></dt>
 <dd><p>Format the constrain equation</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.SubclassSymbolicContext.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.SubclassSymbolicContext.html
index ad9ff610e88..0ec06d0f7d3 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.SubclassSymbolicContext.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.SubclassSymbolicContext.html
@@ -4404,7 +4404,7 @@
 <h1>SubclassSymbolicContext<a class="headerlink" href="#subclasssymboliccontext" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.SubclassSymbolicContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">SubclassSymbolicContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dynamic_sizes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">specialize_on</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">view_base_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape_env_to_source_to_symbol_cache</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inner_contexts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L2151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.SubclassSymbolicContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">SubclassSymbolicContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dynamic_sizes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">constraint_strides</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">specialize_on</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">view_base_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape_env_to_source_to_symbol_cache</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inner_contexts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L2151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.SubclassSymbolicContext" title="Permalink to this definition">#</a></dt>
 <dd><p>The correct symbolic context for a given inner tensor of a traceable tensor subclass
 may differ from that of the outer symbolic context. This structure allows for this
 flexibility, with inner symbolic contexts mapped via attr -&gt; symbolic context.</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.SymbolicContext.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.SymbolicContext.html
index 077c7e48259..0699cd7930c 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.SymbolicContext.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.SymbolicContext.html
@@ -4404,7 +4404,7 @@
 <h1>SymbolicContext<a class="headerlink" href="#symboliccontext" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.SymbolicContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">SymbolicContext</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L2022"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.SymbolicContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">SymbolicContext</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L2022"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.SymbolicContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Data structure specifying how we should create symbols in
 <code class="docutils literal notranslate"><span class="pre">create_symbolic_sizes_strides_storage_offset</span></code>; e.g., should
 they be static or dynamic.</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.canonicalize_bool_expr.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.canonicalize_bool_expr.html
index ab1cb8ff898..2f45fff1d8c 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.canonicalize_bool_expr.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.canonicalize_bool_expr.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.canonicalize_bool_expr<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-canonicalize-bool-expr" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.canonicalize_bool_expr">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">canonicalize_bool_expr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L680"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.canonicalize_bool_expr" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">canonicalize_bool_expr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L680"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.canonicalize_bool_expr" title="Permalink to this definition">#</a></dt>
 <dd><p>Canonicalize a boolean expression by transforming it into a lt / le
 inequality and moving all the non-constant terms to the rhs.
 We canonicalize And / Ors / Not via cnf and then canonicalize their subexpr
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.check_consistent.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.check_consistent.html
index 6086c1e8eb5..0e2f71de5a8 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.check_consistent.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.check_consistent.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.check_consistent<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-check-consistent" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.check_consistent">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">check_consistent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">old</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L477"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.check_consistent" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">check_consistent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">old</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L477"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.check_consistent" title="Permalink to this definition">#</a></dt>
 <dd><p>Test that two “meta” values (typically either Tensor or SymInt) have
 the same values, e.g., after retracing.  If we don’t understand the
 quantities in question, we’ll just skip the consistency check.</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.compute_unbacked_bindings.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.compute_unbacked_bindings.html
index 8eb835495c7..aa4472cbf75 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.compute_unbacked_bindings.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.compute_unbacked_bindings.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.compute_unbacked_bindings<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-compute-unbacked-bindings" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.compute_unbacked_bindings">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">compute_unbacked_bindings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape_env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">old_example_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">peek</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1260"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.compute_unbacked_bindings" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">compute_unbacked_bindings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape_env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">old_example_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">peek</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1260"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.compute_unbacked_bindings" title="Permalink to this definition">#</a></dt>
 <dd><p>After having run fake tensor propagation and producing example_value
 result, traverse example_value looking for freshly bound unbacked
 symbols and record their paths for later.  It is an error if
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.constrain_range.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.constrain_range.html
index 1f837edcafc..dd944317683 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.constrain_range.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.constrain_range.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.constrain_range<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-constrain-range" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.constrain_range">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">constrain_range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1606"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.constrain_range" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">constrain_range</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1606"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.constrain_range" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a constraint that the passed in SymInt must lie between min-max
 inclusive-inclusive, WITHOUT introducing a guard on the SymInt (meaning
 that it can be used on unbacked SymInts).  If min/max are None, we assume
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.constrain_unify.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.constrain_unify.html
index 40e6f503171..b8efb56c96c 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.constrain_unify.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.constrain_unify.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.constrain_unify<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-constrain-unify" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.constrain_unify">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">constrain_unify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1652"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.constrain_unify" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">constrain_unify</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1652"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.constrain_unify" title="Permalink to this definition">#</a></dt>
 <dd><p>Given two SymInts, constrain them so that they must be equal.  NB:
 this will not work with SymInts that represent nontrivial expressions
 (yet!)</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_or_false.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_or_false.html
index 41ea8f18555..bb0dc2ca9dc 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_or_false.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_or_false.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.guard_or_false<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-guard-or-false" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.guard_or_false">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">guard_or_false</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1396"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.guard_or_false" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">guard_or_false</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1396"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.guard_or_false" title="Permalink to this definition">#</a></dt>
 <dd><p>Try to guard a, if data dependent error encountered just return false.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_or_true.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_or_true.html
index ce3681a64b8..3909bb25fc2 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_or_true.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_or_true.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.guard_or_true<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-guard-or-true" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.guard_or_true">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">guard_or_true</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1403"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.guard_or_true" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">guard_or_true</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1403"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.guard_or_true" title="Permalink to this definition">#</a></dt>
 <dd><p>Try to guard a, if data dependent error encountered just return true.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_size_oblivious.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_size_oblivious.html
index 70d70b3c275..13499695460 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_size_oblivious.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.guard_size_oblivious.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.guard_size_oblivious<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-guard-size-oblivious" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.guard_size_oblivious">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">guard_size_oblivious</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L461"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.guard_size_oblivious" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">guard_size_oblivious</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L461"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.guard_size_oblivious" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a guard on a symbolic boolean expression in a size oblivious way.
 This is typically used when a non-oblivious test would result in a guard
 on a data dependent value of which we don’t know the value of at compile time.
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.has_free_symbols.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.has_free_symbols.html
index ed9f99ad856..3142db050a4 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.has_free_symbols.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.has_free_symbols.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.has_free_symbols<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-has-free-symbols" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.has_free_symbols">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">has_free_symbols</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L941"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.has_free_symbols" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">has_free_symbols</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">val</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L941"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.has_free_symbols" title="Permalink to this definition">#</a></dt>
 <dd><p>Faster version of bool(free_symbols(val))</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.has_free_unbacked_symbols.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.has_free_unbacked_symbols.html
index 1384d677302..ee743dbf597 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.has_free_unbacked_symbols.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.has_free_unbacked_symbols.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.has_free_unbacked_symbols<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-has-free-unbacked-symbols" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.has_free_unbacked_symbols">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">has_free_unbacked_symbols</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L946"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.has_free_unbacked_symbols" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">has_free_unbacked_symbols</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L946"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.has_free_unbacked_symbols" title="Permalink to this definition">#</a></dt>
 <dd><p>Faster version of bool(free_unbacked_symbols(val))</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.has_static_value.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.has_static_value.html
index 9683bf434bb..967600d58d3 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.has_static_value.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.has_static_value.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.has_static_value<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-has-static-value" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.has_static_value">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">has_static_value</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L438"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.has_static_value" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">has_static_value</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L438"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.has_static_value" title="Permalink to this definition">#</a></dt>
 <dd><p>User-code friendly utility to check if a value is static or dynamic.
 Returns true if given a constant, or a symbolic expression with a fixed value.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.hint_int.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.hint_int.html
index b0a1c00e998..e1d681420f3 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.hint_int.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.hint_int.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.hint_int<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-hint-int" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.hint_int">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">hint_int</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L356"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.hint_int" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">hint_int</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L356"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.hint_int" title="Permalink to this definition">#</a></dt>
 <dd><p>Retrieve the hint for an int (based on the underlying real values as observed
 at runtime).  If no hint is available (e.g., because data dependent shapes),
 if fallback is not None, use that instead (otherwise raise an error).</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.is_accessor_node.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.is_accessor_node.html
index 8daf3ae2bab..df249cc8ff2 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.is_accessor_node.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.is_accessor_node.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.is_accessor_node<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-is-accessor-node" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.is_accessor_node">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">is_accessor_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L648"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.is_accessor_node" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">is_accessor_node</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L648"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.is_accessor_node" title="Permalink to this definition">#</a></dt>
 <dd><p>Helper function to determine if a node is trying to access
 a symbolic integer such as size, stride, offset or item. Currently
 primarily only used in a DCE pass to figure out purity.</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_bool.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_bool.html
index 415e187bbe0..8f05b91a62c 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_bool.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_bool.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.is_concrete_bool<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-is-concrete-bool" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.is_concrete_bool">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">is_concrete_bool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.is_concrete_bool" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">is_concrete_bool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.is_concrete_bool" title="Permalink to this definition">#</a></dt>
 <dd><p>Utility to check if underlying object
 in SymBool is concrete value. Also returns
 true if integer is passed in.</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_float.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_float.html
index 08fd55d4b73..5d244dea150 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_float.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_float.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.is_concrete_float<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-is-concrete-float" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.is_concrete_float">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">is_concrete_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.is_concrete_float" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">is_concrete_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.is_concrete_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Utility to check if underlying object
 in SymInt is concrete value. Also returns
 true if integer is passed in.</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_int.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_int.html
index 0bceb1f340c..eb7976366c6 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_int.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.is_concrete_int.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.is_concrete_int<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-is-concrete-int" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.is_concrete_int">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">is_concrete_int</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.is_concrete_int" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">is_concrete_int</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.is_concrete_int" title="Permalink to this definition">#</a></dt>
 <dd><p>Utility to check if underlying object
 in SymInt is concrete value. Also returns
 true if integer is passed in.</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.lru_cache.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.lru_cache.html
index c7a6800443e..ba7daa5c32f 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.lru_cache.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.lru_cache.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.lru_cache<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-lru-cache" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.lru_cache">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">lru_cache</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">maxsize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.lru_cache" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">lru_cache</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">maxsize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.lru_cache" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p>Callable[[Callable[…, _T]], functools._lru_cache_wrapper[_T]]</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.rebind_unbacked.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.rebind_unbacked.html
index 0f31ddcbdaa..3ddf4af81c2 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.rebind_unbacked.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.rebind_unbacked.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.rebind_unbacked<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-rebind-unbacked" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.rebind_unbacked">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">rebind_unbacked</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape_env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">result</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L527"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.rebind_unbacked" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">rebind_unbacked</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape_env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">result</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L527"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.rebind_unbacked" title="Permalink to this definition">#</a></dt>
 <dd><p>Suppose we are retracing a pre-existing FX graph that previously had
 fake tensor propagation (and therefore unbacked SymInts).  When we retrace,
 we re-propagate fake tensors, which results in new unbacked SymInts.
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.resolve_unbacked_bindings.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.resolve_unbacked_bindings.html
index a4e2449f035..c6e280cce72 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.resolve_unbacked_bindings.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.resolve_unbacked_bindings.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.resolve_unbacked_bindings<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-resolve-unbacked-bindings" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.resolve_unbacked_bindings">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">resolve_unbacked_bindings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape_env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bindings</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L506"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.resolve_unbacked_bindings" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">resolve_unbacked_bindings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">shape_env</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bindings</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L506"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.resolve_unbacked_bindings" title="Permalink to this definition">#</a></dt>
 <dd><p>When we do fake tensor prop, we oftentimes will allocate new unbacked symints.
 We then run proxy tensor mode, which populates node.meta[“unbacked_bindings”]
 with these new symints. To ensure consistency we use PropagateUnbackedSymInts
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.statically_known_false.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.statically_known_false.html
index be200b5d6f7..5978b226bd8 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.statically_known_false.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.statically_known_false.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.statically_known_false<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-statically-known-false" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.statically_known_false">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">statically_known_false</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1428"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.statically_known_false" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">statically_known_false</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1428"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.statically_known_false" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if x can be simplified to a constant and is False.
 If x cannot be evaluated from static, we return False</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.statically_known_true.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.statically_known_true.html
index 0684aa9f158..ca696928402 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.statically_known_true.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.statically_known_true.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.statically_known_true<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-statically-known-true" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.statically_known_true">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">statically_known_true</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1451"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.statically_known_true" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">statically_known_true</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1451"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.statically_known_true" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if x can be simplified to a constant and is true.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_and.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_and.html
index 7f9a8d16241..6bd3655883d 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_and.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_and.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.sym_and<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-sym-and" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.sym_and">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">sym_and</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">others</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1472"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.sym_and" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">sym_and</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">others</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1472"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.sym_and" title="Permalink to this definition">#</a></dt>
 <dd><p>and, but for symbolic expressions, without bool casting.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_eq.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_eq.html
index 3f85370a190..f978c9b664a 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_eq.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_eq.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.sym_eq<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-sym-eq" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.sym_eq">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">sym_eq</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1483"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.sym_eq" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">sym_eq</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1483"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.sym_eq" title="Permalink to this definition">#</a></dt>
 <dd><p>Like ==, but when run on list/tuple, it will recursively test equality
 and use sym_and to join the results together, without guarding.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_or.html b/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_or.html
index 658f422acf6..357832d30d5 100644
--- a/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_or.html
+++ b/2.9/generated/torch.fx.experimental.symbolic_shapes.sym_or.html
@@ -4404,7 +4404,7 @@
 <h1>torch.fx.experimental.symbolic_shapes.sym_or<a class="headerlink" href="#torch-fx-experimental-symbolic-shapes-sym-or" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.fx.experimental.symbolic_shapes.sym_or">
-<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">sym_or</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">others</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/fx/experimental/symbolic_shapes.py#L1498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.sym_or" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.fx.experimental.symbolic_shapes.</span></span><span class="sig-name descname"><span class="pre">sym_or</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">others</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/fx/experimental/symbolic_shapes.py#L1498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.fx.experimental.symbolic_shapes.sym_or" title="Permalink to this definition">#</a></dt>
 <dd><p>or, but for symbolic expressions, without bool casting.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.get_default_device.html b/2.9/generated/torch.get_default_device.html
index 129b134337d..d3603fd698a 100644
--- a/2.9/generated/torch.get_default_device.html
+++ b/2.9/generated/torch.get_default_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.get_default_device<a class="headerlink" href="#torch-get-default-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.get_default_device">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_default_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_default_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_default_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_default_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Gets the default <code class="docutils literal notranslate"><span class="pre">torch.Tensor</span></code> to be allocated on <code class="docutils literal notranslate"><span class="pre">device</span></code></p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.get_deterministic_debug_mode.html b/2.9/generated/torch.get_deterministic_debug_mode.html
index 4d59aa9f1b8..f46ccc10a18 100644
--- a/2.9/generated/torch.get_deterministic_debug_mode.html
+++ b/2.9/generated/torch.get_deterministic_debug_mode.html
@@ -4404,7 +4404,7 @@
 <h1>torch.get_deterministic_debug_mode<a class="headerlink" href="#torch-get-deterministic-debug-mode" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.get_deterministic_debug_mode">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_deterministic_debug_mode</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_deterministic_debug_mode" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_deterministic_debug_mode</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1532"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_deterministic_debug_mode" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the current value of the debug mode for deterministic
 operations. Refer to <a class="reference internal" href="torch.set_deterministic_debug_mode.html#torch.set_deterministic_debug_mode" title="torch.set_deterministic_debug_mode"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.set_deterministic_debug_mode()</span></code></a>
 documentation for more details.</p>
diff --git a/2.9/generated/torch.get_device_module.html b/2.9/generated/torch.get_device_module.html
index 60696cf5778..bfd013c7644 100644
--- a/2.9/generated/torch.get_device_module.html
+++ b/2.9/generated/torch.get_device_module.html
@@ -4404,7 +4404,7 @@
 <h1>torch.get_device_module<a class="headerlink" href="#torch-get-device-module" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.get_device_module">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_device_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L2760"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_device_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_device_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L2760"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_device_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the module associated with a given device(e.g., torch.device(‘cuda’), “mtia:0”, “xpu”, …).
 If no device is given, return the module for the current accelerator or CPU if none is present.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.get_float32_matmul_precision.html b/2.9/generated/torch.get_float32_matmul_precision.html
index cd676f0d7b8..73ad9a8229f 100644
--- a/2.9/generated/torch.get_float32_matmul_precision.html
+++ b/2.9/generated/torch.get_float32_matmul_precision.html
@@ -4404,7 +4404,7 @@
 <h1>torch.get_float32_matmul_precision<a class="headerlink" href="#torch-get-float32-matmul-precision" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.get_float32_matmul_precision">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_float32_matmul_precision</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1547"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_float32_matmul_precision" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_float32_matmul_precision</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1547"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_float32_matmul_precision" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the current value of float32 matrix multiplication precision. Refer to
 <a class="reference internal" href="torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision" title="torch.set_float32_matmul_precision"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.set_float32_matmul_precision()</span></code></a> documentation for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.get_rng_state.html b/2.9/generated/torch.get_rng_state.html
index 6562713a78a..9460ba6fd5f 100644
--- a/2.9/generated/torch.get_rng_state.html
+++ b/2.9/generated/torch.get_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.get_rng_state<a class="headerlink" href="#torch-get-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.get_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.get_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the random number generator state as a <cite>torch.ByteTensor</cite>.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.initial_seed.html b/2.9/generated/torch.initial_seed.html
index 45ca4d7652c..79bc74fc406 100644
--- a/2.9/generated/torch.initial_seed.html
+++ b/2.9/generated/torch.initial_seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.initial_seed<a class="headerlink" href="#torch-initial-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.initial_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">initial_seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.initial_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">initial_seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.initial_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the initial seed for generating random numbers as a
 Python <cite>long</cite>.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.is_deterministic_algorithms_warn_only_enabled.html b/2.9/generated/torch.is_deterministic_algorithms_warn_only_enabled.html
index 541ebd4e6d9..48820724b7e 100644
--- a/2.9/generated/torch.is_deterministic_algorithms_warn_only_enabled.html
+++ b/2.9/generated/torch.is_deterministic_algorithms_warn_only_enabled.html
@@ -4404,7 +4404,7 @@
 <h1>torch.is_deterministic_algorithms_warn_only_enabled<a class="headerlink" href="#torch-is-deterministic-algorithms-warn-only-enabled" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.is_deterministic_algorithms_warn_only_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">is_deterministic_algorithms_warn_only_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1480"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.is_deterministic_algorithms_warn_only_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">is_deterministic_algorithms_warn_only_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1480"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.is_deterministic_algorithms_warn_only_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if the global deterministic flag is set to warn only.
 Refer to <a class="reference internal" href="torch.use_deterministic_algorithms.html#torch.use_deterministic_algorithms" title="torch.use_deterministic_algorithms"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.use_deterministic_algorithms()</span></code></a> documentation for more
 details.</p>
diff --git a/2.9/generated/torch.is_storage.html b/2.9/generated/torch.is_storage.html
index d7b86238a70..fec8c4096b9 100644
--- a/2.9/generated/torch.is_storage.html
+++ b/2.9/generated/torch.is_storage.html
@@ -4404,7 +4404,7 @@
 <h1>torch.is_storage<a class="headerlink" href="#torch-is-storage" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.is_storage">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">is_storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.is_storage" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">is_storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.is_storage" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if <cite>obj</cite> is a PyTorch storage object.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.is_tensor.html b/2.9/generated/torch.is_tensor.html
index 61bae0f694f..eb06fb9bd94 100644
--- a/2.9/generated/torch.is_tensor.html
+++ b/2.9/generated/torch.is_tensor.html
@@ -4404,7 +4404,7 @@
 <h1>torch.is_tensor<a class="headerlink" href="#torch-is-tensor" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.is_tensor">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">is_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.is_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">is_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.is_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if <cite>obj</cite> is a PyTorch tensor.</p>
 <p>Note that this function is simply doing <code class="docutils literal notranslate"><span class="pre">isinstance(obj,</span> <span class="pre">Tensor)</span></code>.
 Using that <code class="docutils literal notranslate"><span class="pre">isinstance</span></code> check is better for type checking with mypy,
diff --git a/2.9/generated/torch.is_warn_always_enabled.html b/2.9/generated/torch.is_warn_always_enabled.html
index 2418646734f..913057a28f4 100644
--- a/2.9/generated/torch.is_warn_always_enabled.html
+++ b/2.9/generated/torch.is_warn_always_enabled.html
@@ -4404,7 +4404,7 @@
 <h1>torch.is_warn_always_enabled<a class="headerlink" href="#torch-is-warn-always-enabled" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.is_warn_always_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">is_warn_always_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.is_warn_always_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">is_warn_always_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.is_warn_always_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if the global warn_always flag is turned on. Refer to
 <a class="reference internal" href="torch.set_warn_always.html#torch.set_warn_always" title="torch.set_warn_always"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.set_warn_always()</span></code></a> documentation for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.jit.ScriptModule.html b/2.9/generated/torch.jit.ScriptModule.html
index 461830ce467..d9f8fe9f408 100644
--- a/2.9/generated/torch.jit.ScriptModule.html
+++ b/2.9/generated/torch.jit.ScriptModule.html
@@ -4404,7 +4404,7 @@
 <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">ScriptModule</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_script.py#L513"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">ScriptModule</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_script.py#L513"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper for C++ torch::jit::Module with methods, attributes, and parameters.</p>
 <p>A wrapper around C++ <code class="docutils literal notranslate"><span class="pre">torch::jit::Module</span></code>. <code class="docutils literal notranslate"><span class="pre">ScriptModule</span></code>s
 contain methods, attributes, parameters, and
@@ -4413,7 +4413,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.add_module">
-<span class="sig-name descname"><span class="pre">add_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L639"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.add_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L639"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.add_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a child module to the current module.</p>
 <p>The module can be accessed as an attribute using the given name.</p>
 <dl class="field-list simple">
@@ -4429,7 +4429,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.apply">
-<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.apply" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every submodule (as returned by <code class="docutils literal notranslate"><span class="pre">.children()</span></code>) as well as self.</p>
 <p>Typical use includes initializing the parameters of a model
 (see also <a class="reference internal" href="../nn.init.html#nn-init-doc"><span class="std std-ref">torch.nn.init</span></a>).</p>
@@ -4471,7 +4471,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.bfloat16">
-<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.bfloat16" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.bfloat16" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">bfloat16</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4489,7 +4489,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.buffers">
-<span class="sig-name descname"><span class="pre">buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2713"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2713"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module buffers.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4515,7 +4515,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.children">
-<span class="sig-name descname"><span class="pre">children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2767"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.children" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2767"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.children" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over immediate children modules.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -4546,7 +4546,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.compile">
-<span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L3030"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.compile" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L3030"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.compile" title="Permalink to this definition">#</a></dt>
 <dd><p>Compile this Module’s forward using <a class="reference internal" href="torch.compile.html#torch.compile" title="torch.compile"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.compile()</span></code></a>.</p>
 <p>This Module’s <cite>__call__</cite> method is compiled and all arguments are passed as-is
 to <a class="reference internal" href="torch.compile.html#torch.compile" title="torch.compile"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.compile()</span></code></a>.</p>
@@ -4555,7 +4555,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.cpu">
-<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.cpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.cpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the CPU.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4573,7 +4573,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.cuda">
-<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.cuda" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.cuda" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the GPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -4598,7 +4598,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.double">
-<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.double" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.double" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">double</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4616,7 +4616,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.eval">
-<span class="sig-name descname"><span class="pre">eval</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2894"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.eval" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">eval</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2894"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.eval" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module in evaluation mode.</p>
 <p>This has an effect only on certain modules. See the documentation of
 particular modules for details of their behaviors in training/evaluation
@@ -4637,7 +4637,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2970"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2970"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <p>To print customized extra information, you should re-implement
 this method in your own modules. Both single-line and multi-line
@@ -4651,7 +4651,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.float">
-<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.float" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.float" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">float</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4669,7 +4669,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.get_buffer">
-<span class="sig-name descname"><span class="pre">get_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.get_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.get_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the buffer given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>See the docstring for <code class="docutils literal notranslate"><span class="pre">get_submodule</span></code> for a more detailed
 explanation of this method’s functionality as well as how to
@@ -4696,7 +4696,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.get_extra_state">
-<span class="sig-name descname"><span class="pre">get_extra_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L889"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.get_extra_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_extra_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L889"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.get_extra_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Return any extra state to include in the module’s state_dict.</p>
 <p>Implement this and a corresponding <a class="reference internal" href="#torch.jit.ScriptModule.set_extra_state" title="torch.jit.ScriptModule.set_extra_state"><code class="xref py py-func docutils literal notranslate"><span class="pre">set_extra_state()</span></code></a> for your module
 if you need to store extra state. This function is called when building the
@@ -4717,7 +4717,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.get_parameter">
-<span class="sig-name descname"><span class="pre">get_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.get_parameter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.get_parameter" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the parameter given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>See the docstring for <code class="docutils literal notranslate"><span class="pre">get_submodule</span></code> for a more detailed
 explanation of this method’s functionality as well as how to
@@ -4744,7 +4744,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.get_submodule">
-<span class="sig-name descname"><span class="pre">get_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L671"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.get_submodule" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L671"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.get_submodule" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the submodule given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>For example, let’s say you have an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> <code class="docutils literal notranslate"><span class="pre">A</span></code> that
 looks like this:</p>
@@ -4799,7 +4799,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.half">
-<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.half" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.half" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">half</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4824,7 +4824,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.ipu">
-<span class="sig-name descname"><span class="pre">ipu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.ipu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">ipu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.ipu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the IPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -4849,7 +4849,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assign</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2522"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assign</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2522"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy parameters and buffers from <a class="reference internal" href="#torch.jit.ScriptModule.state_dict" title="torch.jit.ScriptModule.state_dict"><code class="xref py py-attr docutils literal notranslate"><span class="pre">state_dict</span></code></a> into this module and its descendants.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">strict</span></code> is <code class="docutils literal notranslate"><span class="pre">True</span></code>, then
 the keys of <a class="reference internal" href="#torch.jit.ScriptModule.state_dict" title="torch.jit.ScriptModule.state_dict"><code class="xref py py-attr docutils literal notranslate"><span class="pre">state_dict</span></code></a> must exactly match the keys returned
@@ -4904,7 +4904,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.modules">
-<span class="sig-name descname"><span class="pre">modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2796"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2796"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over all modules in the network.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -4936,7 +4936,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.mtia">
-<span class="sig-name descname"><span class="pre">mtia</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.mtia" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mtia</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.mtia" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the MTIA.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -4961,7 +4961,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.named_buffers">
-<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.named_buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.named_buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4990,7 +4990,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.named_children">
-<span class="sig-name descname"><span class="pre">named_children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.named_children" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.named_children" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -5010,7 +5010,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.named_modules">
-<span class="sig-name descname"><span class="pre">named_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.named_modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.named_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5047,7 +5047,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.named_parameters">
-<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2681"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.named_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2681"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.named_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5077,7 +5077,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.parameters">
-<span class="sig-name descname"><span class="pre">parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2656"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2656"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module parameters.</p>
 <p>This is typically passed to an optimizer.</p>
 <dl class="field-list simple">
@@ -5104,7 +5104,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_backward_hook">
-<span class="sig-name descname"><span class="pre">register_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_backward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_backward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook on the module.</p>
 <p>This function is deprecated in favor of <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module.register_full_backward_hook" title="torch.nn.Module.register_full_backward_hook"><code class="xref py py-meth docutils literal notranslate"><span class="pre">register_full_backward_hook()</span></code></a> and
 the behavior of this function will change in future versions.</p>
@@ -5121,7 +5121,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_buffer">
-<span class="sig-name descname"><span class="pre">register_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a buffer to the module.</p>
 <p>This is typically used to register a buffer that should not be
 considered a model parameter. For example, BatchNorm’s <code class="docutils literal notranslate"><span class="pre">running_mean</span></code>
@@ -5153,7 +5153,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_forward_hook">
-<span class="sig-name descname"><span class="pre">register_forward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">always_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_forward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_forward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">always_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_forward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a forward hook on the module.</p>
 <p>The hook will be called every time after <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> has computed an output.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">with_kwargs</span></code> is <code class="docutils literal notranslate"><span class="pre">False</span></code> or not specified, the input contains only
@@ -5204,7 +5204,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_forward_pre_hook">
-<span class="sig-name descname"><span class="pre">register_forward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_forward_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_forward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_forward_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a forward pre-hook on the module.</p>
 <p>The hook will be called every time before <code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code> is invoked.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">with_kwargs</span></code> is false or not specified, the input contains only
@@ -5254,7 +5254,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_full_backward_hook">
-<span class="sig-name descname"><span class="pre">register_full_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_full_backward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_full_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_full_backward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook on the module.</p>
 <p>The hook will be called every time the gradients with respect to a module are computed, and its firing rules are as follows:</p>
 <blockquote>
@@ -5311,7 +5311,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_full_backward_pre_hook">
-<span class="sig-name descname"><span class="pre">register_full_backward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_full_backward_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_full_backward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_full_backward_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward pre-hook on the module.</p>
 <p>The hook will be called every time the gradients for the module are computed.
 The hook should have the following signature:</p>
@@ -5357,7 +5357,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2312"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2312"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a post-hook to be run after module’s <code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code> is called.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, incompatible_keys) -&gt; None</p>
@@ -5387,7 +5387,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a pre-hook to be run before module’s <code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code> is called.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -&gt; None  # noqa: B950</p>
@@ -5403,7 +5403,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_module">
-<span class="sig-name descname"><span class="pre">register_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Alias for <a class="reference internal" href="#torch.jit.ScriptModule.add_module" title="torch.jit.ScriptModule.add_module"><code class="xref py py-func docutils literal notranslate"><span class="pre">add_module()</span></code></a>.</p>
 <dl class="field-list simple">
 </dl>
@@ -5411,7 +5411,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_parameter">
-<span class="sig-name descname"><span class="pre">register_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_parameter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_parameter" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a parameter to the module.</p>
 <p>The parameter can be accessed as an attribute using given name.</p>
 <dl class="field-list simple">
@@ -5430,7 +5430,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a post-hook for the <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module.state_dict" title="torch.nn.Module.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> method.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, state_dict, prefix, local_metadata) -&gt; None</p>
@@ -5441,7 +5441,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a pre-hook for the <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module.state_dict" title="torch.nn.Module.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> method.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, prefix, keep_vars) -&gt; None</p>
@@ -5453,7 +5453,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.requires_grad_">
-<span class="sig-name descname"><span class="pre">requires_grad_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2912"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.requires_grad_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">requires_grad_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2912"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.requires_grad_" title="Permalink to this definition">#</a></dt>
 <dd><p>Change if autograd should record operations on parameters in this module.</p>
 <p>This method sets the parameters’ <code class="xref py py-attr docutils literal notranslate"><span class="pre">requires_grad</span></code> attributes
 in-place.</p>
@@ -5477,7 +5477,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.save">
-<span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_script.py#L742"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.save" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_script.py#L742"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.save" title="Permalink to this definition">#</a></dt>
 <dd><p>Save with a file-like object.</p>
 <p>save(f, _extra_files={})</p>
 <p>See <a class="reference internal" href="torch.jit.save.html#torch.jit.save" title="torch.jit.save"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.jit.save</span></code></a> which accepts a file-like object.
@@ -5487,7 +5487,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.set_extra_state">
-<span class="sig-name descname"><span class="pre">set_extra_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.set_extra_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_extra_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.set_extra_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Set extra state contained in the loaded <cite>state_dict</cite>.</p>
 <p>This function is called from <a class="reference internal" href="#torch.jit.ScriptModule.load_state_dict" title="torch.jit.ScriptModule.load_state_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> to handle any extra state
 found within the <cite>state_dict</cite>. Implement this function and a corresponding
@@ -5502,7 +5502,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.set_submodule">
-<span class="sig-name descname"><span class="pre">set_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.set_submodule" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.set_submodule" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the submodule given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -5560,7 +5560,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.share_memory">
-<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.share_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.share_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.Tensor.share_memory_.html#torch.Tensor.share_memory_" title="torch.Tensor.share_memory_"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.Tensor.share_memory_()</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5571,7 +5571,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_vars</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_vars</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary containing references to the whole state of the module.</p>
 <p>Both parameters and persistent buffers (e.g. running averages) are
 included. Keys are corresponding parameter and buffer names.
@@ -5624,27 +5624,27 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.to">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.to" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.to" title="Permalink to this definition">#</a></dt>
 <dd><p>Move and/or cast the parameters and buffers.</p>
 <p>This can be called as</p>
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memory_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.channels_last</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memory_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.channels_last</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <p>Its signature is similar to <a class="reference internal" href="torch.Tensor.to.html#torch.Tensor.to" title="torch.Tensor.to"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.Tensor.to()</span></code></a>, but only accepts
@@ -5723,7 +5723,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.to_empty">
-<span class="sig-name descname"><span class="pre">to_empty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.to_empty" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_empty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.to_empty" title="Permalink to this definition">#</a></dt>
 <dd><p>Move the parameters and buffers to the specified device without copying storage.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5745,7 +5745,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.train">
-<span class="sig-name descname"><span class="pre">train</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2872"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.train" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">train</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2872"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.train" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module in training mode.</p>
 <p>This has an effect only on certain modules. See the documentation of
 particular modules for details of their behaviors in training/evaluation
@@ -5767,7 +5767,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.type">
-<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dst_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.type" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dst_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.type" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all parameters and buffers to <code class="xref py py-attr docutils literal notranslate"><span class="pre">dst_type</span></code>.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -5788,7 +5788,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.xpu">
-<span class="sig-name descname"><span class="pre">xpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.xpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">xpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.xpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the XPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing optimizer if the module will
@@ -5813,7 +5813,7 @@ <h1>ScriptModule<a class="headerlink" href="#scriptmodule" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.jit.ScriptModule.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2935"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2935"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ScriptModule.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset gradients of all model parameters.</p>
 <p>See similar function under <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.optim.Optimizer</span></code></a> for more context.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.jit.annotate.html b/2.9/generated/torch.jit.annotate.html
index d1cd69169c4..fe9695e8715 100644
--- a/2.9/generated/torch.jit.annotate.html
+++ b/2.9/generated/torch.jit.annotate.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.annotate<a class="headerlink" href="#torch-jit-annotate" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.annotate">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">annotate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">the_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">the_value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/__init__.py#L129"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.annotate" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">annotate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">the_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">the_value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/__init__.py#L129"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.annotate" title="Permalink to this definition">#</a></dt>
 <dd><p>Use to give type of <cite>the_value</cite> in TorchScript compiler.</p>
 <p>This method is a pass-through function that returns <cite>the_value</cite>, used to hint TorchScript
 compiler the type of <cite>the_value</cite>. It is a no-op when running outside of TorchScript.</p>
diff --git a/2.9/generated/torch.jit.enable_onednn_fusion.html b/2.9/generated/torch.jit.enable_onednn_fusion.html
index 3a52731595c..63af8a3cf2b 100644
--- a/2.9/generated/torch.jit.enable_onednn_fusion.html
+++ b/2.9/generated/torch.jit.enable_onednn_fusion.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.enable_onednn_fusion<a class="headerlink" href="#torch-jit-enable-onednn-fusion" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.enable_onednn_fusion">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">enable_onednn_fusion</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/__init__.py#L282"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.enable_onednn_fusion" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">enable_onednn_fusion</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/__init__.py#L282"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.enable_onednn_fusion" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable or disables onednn JIT fusion based on the parameter <cite>enabled</cite>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.jit.fork.html b/2.9/generated/torch.jit.fork.html
index 4734e4aa9e2..cd62f0a1de9 100644
--- a/2.9/generated/torch.jit.fork.html
+++ b/2.9/generated/torch.jit.fork.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.fork<a class="headerlink" href="#torch-jit-fork" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.fork">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">fork</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_async.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.fork" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">fork</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_async.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.fork" title="Permalink to this definition">#</a></dt>
 <dd><p>Create an asynchronous task executing <cite>func</cite> and a reference to the value of the result of this execution.</p>
 <p><cite>fork</cite> will return immediately, so the return value of <cite>func</cite> may not have been computed yet. To force completion
 of the task and access the return value invoke <cite>torch.jit.wait</cite> on the Future. <cite>fork</cite> invoked
diff --git a/2.9/generated/torch.jit.freeze.html b/2.9/generated/torch.jit.freeze.html
index afee67d158c..b67563f30f5 100644
--- a/2.9/generated/torch.jit.freeze.html
+++ b/2.9/generated/torch.jit.freeze.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.freeze<a class="headerlink" href="#torch-jit-freeze" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.freeze">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">freeze</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserved_attrs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize_numerics</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_freeze.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.freeze" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">freeze</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserved_attrs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize_numerics</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_freeze.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.freeze" title="Permalink to this definition">#</a></dt>
 <dd><p>Freeze ScriptModule, inline submodules, and attributes as constants.</p>
 <p>Freezing a <a class="reference internal" href="torch.jit.ScriptModule.html#torch.jit.ScriptModule" title="torch.jit.ScriptModule"><code class="xref py py-class docutils literal notranslate"><span class="pre">ScriptModule</span></code></a> will clone it and attempt to inline the cloned
 module’s submodules, parameters, and attributes as constants in the TorchScript IR Graph.
diff --git a/2.9/generated/torch.jit.ignore.html b/2.9/generated/torch.jit.ignore.html
index 02357e6bf8a..1a4701cbbe1 100644
--- a/2.9/generated/torch.jit.ignore.html
+++ b/2.9/generated/torch.jit.ignore.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.ignore<a class="headerlink" href="#torch-jit-ignore" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.ignore">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">ignore</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">drop</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L785"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ignore" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">ignore</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">drop</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L785"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.ignore" title="Permalink to this definition">#</a></dt>
 <dd><p>This decorator indicates to the compiler that a function or method should
 be ignored and left as a Python function. This allows you to leave code in
 your model that is not yet TorchScript compatible. If called from TorchScript,
diff --git a/2.9/generated/torch.jit.interface.html b/2.9/generated/torch.jit.interface.html
index 566c8b7217e..7a2d3a32bcc 100644
--- a/2.9/generated/torch.jit.interface.html
+++ b/2.9/generated/torch.jit.interface.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.interface<a class="headerlink" href="#torch-jit-interface" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.interface">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">interface</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_script.py#L1528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.interface" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">interface</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_script.py#L1528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.interface" title="Permalink to this definition">#</a></dt>
 <dd><p>Decorate to annotate classes or modules of different types.</p>
 <p>This decorator can be used to define an interface that can be used to annotate
 classes or modules of different types. This can be used for to annotate a submodule
diff --git a/2.9/generated/torch.jit.isinstance.html b/2.9/generated/torch.jit.isinstance.html
index fc521658e82..c8e0fede7b1 100644
--- a/2.9/generated/torch.jit.isinstance.html
+++ b/2.9/generated/torch.jit.isinstance.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.isinstance<a class="headerlink" href="#torch-jit-isinstance" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.isinstance">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">isinstance</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/__init__.py#L199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.isinstance" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">isinstance</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/__init__.py#L199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.isinstance" title="Permalink to this definition">#</a></dt>
 <dd><p>Provide container type refinement in TorchScript.</p>
 <p>It can refine parameterized containers of the List, Dict, Tuple, and Optional types. E.g. <code class="docutils literal notranslate"><span class="pre">List[str]</span></code>,
 <code class="docutils literal notranslate"><span class="pre">Dict[str,</span> <span class="pre">List[torch.Tensor]]</span></code>, <code class="docutils literal notranslate"><span class="pre">Optional[Tuple[int,str,int]]</span></code>. It can also
diff --git a/2.9/generated/torch.jit.load.html b/2.9/generated/torch.jit.load.html
index db7a49a28c5..ccb0e332f0a 100644
--- a/2.9/generated/torch.jit.load.html
+++ b/2.9/generated/torch.jit.load.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.load<a class="headerlink" href="#torch-jit-load" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.load">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_restore_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_serialization.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.load" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_restore_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_serialization.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.load" title="Permalink to this definition">#</a></dt>
 <dd><p>Load a <a class="reference internal" href="torch.jit.ScriptModule.html#torch.jit.ScriptModule" title="torch.jit.ScriptModule"><code class="xref py py-class docutils literal notranslate"><span class="pre">ScriptModule</span></code></a> or <a class="reference internal" href="torch.jit.ScriptFunction.html#torch.jit.ScriptFunction" title="torch.jit.ScriptFunction"><code class="xref py py-class docutils literal notranslate"><span class="pre">ScriptFunction</span></code></a> previously saved with <a class="reference internal" href="torch.jit.save.html#torch.jit.save" title="torch.jit.save"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.jit.save</span></code></a>.</p>
 <p>All previously saved modules, no matter their device, are first loaded onto CPU,
 and then are moved to the devices they were saved from. If this fails (e.g.
diff --git a/2.9/generated/torch.jit.onednn_fusion_enabled.html b/2.9/generated/torch.jit.onednn_fusion_enabled.html
index 1c43fb4a7b3..811bd2a67c8 100644
--- a/2.9/generated/torch.jit.onednn_fusion_enabled.html
+++ b/2.9/generated/torch.jit.onednn_fusion_enabled.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.onednn_fusion_enabled<a class="headerlink" href="#torch-jit-onednn-fusion-enabled" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.onednn_fusion_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">onednn_fusion_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/__init__.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.onednn_fusion_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">onednn_fusion_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/__init__.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.onednn_fusion_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether onednn JIT fusion is enabled.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.jit.optimize_for_inference.html b/2.9/generated/torch.jit.optimize_for_inference.html
index 024d0575fa3..34bf32e3a19 100644
--- a/2.9/generated/torch.jit.optimize_for_inference.html
+++ b/2.9/generated/torch.jit.optimize_for_inference.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.optimize_for_inference<a class="headerlink" href="#torch-jit-optimize-for-inference" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.optimize_for_inference">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">optimize_for_inference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">other_methods</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_freeze.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.optimize_for_inference" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">optimize_for_inference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">other_methods</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_freeze.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.optimize_for_inference" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a set of optimization passes to optimize a model for the purposes of inference.</p>
 <p>If the model is not already frozen, optimize_for_inference
 will invoke <cite>torch.jit.freeze</cite> automatically.</p>
diff --git a/2.9/generated/torch.jit.save.html b/2.9/generated/torch.jit.save.html
index 3e6cf1a6c51..ec99bbb059d 100644
--- a/2.9/generated/torch.jit.save.html
+++ b/2.9/generated/torch.jit.save.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.save<a class="headerlink" href="#torch-jit-save" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.save">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_serialization.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.save" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_extra_files</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_serialization.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.save" title="Permalink to this definition">#</a></dt>
 <dd><p>Save an offline version of this module for use in a separate process.</p>
 <p>The saved module serializes all of the methods, submodules, parameters, and
 attributes of this module. It can be loaded into the C++ API using
diff --git a/2.9/generated/torch.jit.script.html b/2.9/generated/torch.jit.script.html
index e85165b1794..1a29dda9e06 100644
--- a/2.9/generated/torch.jit.script.html
+++ b/2.9/generated/torch.jit.script.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.script<a class="headerlink" href="#torch-jit-script" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.script">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">script</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_frames_up</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_rcb</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_script.py#L1223"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.script" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">script</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_frames_up</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_rcb</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_script.py#L1223"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.script" title="Permalink to this definition">#</a></dt>
 <dd><p>Script the function.</p>
 <p>Scripting a function or <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> will inspect the source code, compile
 it as TorchScript code using the TorchScript compiler, and return a <a class="reference internal" href="torch.jit.ScriptModule.html#torch.jit.ScriptModule" title="torch.jit.ScriptModule"><code class="xref py py-class docutils literal notranslate"><span class="pre">ScriptModule</span></code></a> or
diff --git a/2.9/generated/torch.jit.script_if_tracing.html b/2.9/generated/torch.jit.script_if_tracing.html
index 362ef509db3..8bbd3b157c5 100644
--- a/2.9/generated/torch.jit.script_if_tracing.html
+++ b/2.9/generated/torch.jit.script_if_tracing.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.script_if_tracing<a class="headerlink" href="#torch-jit-script-if-tracing" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.script_if_tracing">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">script_if_tracing</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/__init__.py#L177"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.script_if_tracing" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">script_if_tracing</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/__init__.py#L177"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.script_if_tracing" title="Permalink to this definition">#</a></dt>
 <dd><p>Compiles <code class="docutils literal notranslate"><span class="pre">fn</span></code> when it is first called during tracing.</p>
 <p><code class="docutils literal notranslate"><span class="pre">torch.jit.script</span></code> has a non-negligible start up time when it is first called due to
 lazy-initializations of many compiler builtins. Therefore you should not use
diff --git a/2.9/generated/torch.jit.set_fusion_strategy.html b/2.9/generated/torch.jit.set_fusion_strategy.html
index d7bfd1dce34..7b092ffb832 100644
--- a/2.9/generated/torch.jit.set_fusion_strategy.html
+++ b/2.9/generated/torch.jit.set_fusion_strategy.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.set_fusion_strategy<a class="headerlink" href="#torch-jit-set-fusion-strategy" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.set_fusion_strategy">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">set_fusion_strategy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">strategy</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_fuser.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.set_fusion_strategy" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">set_fusion_strategy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">strategy</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_fuser.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.set_fusion_strategy" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the type and number of specializations that can occur during fusion.</p>
 <p>Usage: provide a list of pairs (type, depth) where type is one of “STATIC” or “DYNAMIC”
 and depth is an integer.</p>
diff --git a/2.9/generated/torch.jit.strict_fusion.html b/2.9/generated/torch.jit.strict_fusion.html
index c5ccc16cc81..e6b6eddf6a9 100644
--- a/2.9/generated/torch.jit.strict_fusion.html
+++ b/2.9/generated/torch.jit.strict_fusion.html
@@ -4404,7 +4404,7 @@
 <h1>strict_fusion<a class="headerlink" href="#strict-fusion" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.jit.strict_fusion">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">strict_fusion</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/__init__.py#L242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.strict_fusion" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">strict_fusion</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/__init__.py#L242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.strict_fusion" title="Permalink to this definition">#</a></dt>
 <dd><p>Give errors if not all nodes have been fused in inference, or symbolically differentiated in training.</p>
 <p>Example:
 Forcing fusion of additions.</p>
diff --git a/2.9/generated/torch.jit.trace.html b/2.9/generated/torch.jit.trace.html
index f1da0281fb6..ab2df480433 100644
--- a/2.9/generated/torch.jit.trace.html
+++ b/2.9/generated/torch.jit.trace.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.trace<a class="headerlink" href="#torch-jit-trace" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.trace">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_trace=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_tolerance=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_force_outplace=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_module_class=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_compilation_unit=&lt;torch.jit.CompilationUnit</span> <span class="pre">object&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_kwarg_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_store_inputs=True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_trace.py#L825"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.trace" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_trace=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_tolerance=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_force_outplace=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_module_class=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_compilation_unit=&lt;torch.jit.CompilationUnit</span> <span class="pre">object&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_kwarg_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_store_inputs=True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_trace.py#L825"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.trace" title="Permalink to this definition">#</a></dt>
 <dd><p>Trace a function and return an executable  or <a class="reference internal" href="torch.jit.ScriptFunction.html#torch.jit.ScriptFunction" title="torch.jit.ScriptFunction"><code class="xref py py-class docutils literal notranslate"><span class="pre">ScriptFunction</span></code></a> that will be optimized using just-in-time compilation.</p>
 <p>Tracing is ideal for code that operates only on
 <code class="docutils literal notranslate"><span class="pre">Tensor</span></code>\s and lists, dictionaries, and
diff --git a/2.9/generated/torch.jit.trace_module.html b/2.9/generated/torch.jit.trace_module.html
index fd34ba9980e..d9259b41775 100644
--- a/2.9/generated/torch.jit.trace_module.html
+++ b/2.9/generated/torch.jit.trace_module.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.trace_module<a class="headerlink" href="#torch-jit-trace-module" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.trace_module">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">trace_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_trace=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_tolerance=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_force_outplace=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_module_class=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_compilation_unit=&lt;torch.jit.CompilationUnit</span> <span class="pre">object&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs_is_kwarg=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_store_inputs=True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_trace.py#L1019"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.trace_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">trace_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_trace=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_inputs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_tolerance=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_force_outplace=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_module_class=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_compilation_unit=&lt;torch.jit.CompilationUnit</span> <span class="pre">object&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">example_inputs_is_kwarg=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_store_inputs=True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_trace.py#L1019"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.trace_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Trace a module and return an executable <a class="reference internal" href="torch.jit.ScriptModule.html#torch.jit.ScriptModule" title="torch.jit.ScriptModule"><code class="xref py py-class docutils literal notranslate"><span class="pre">ScriptModule</span></code></a> that will be optimized using just-in-time compilation.</p>
 <p>When a module is passed to <a class="reference internal" href="torch.jit.trace.html#torch.jit.trace" title="torch.jit.trace"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.jit.trace</span></code></a>, only
 the <code class="docutils literal notranslate"><span class="pre">forward</span></code> method is run and traced. With <code class="docutils literal notranslate"><span class="pre">trace_module</span></code>, you can specify a dictionary of
diff --git a/2.9/generated/torch.jit.unused.html b/2.9/generated/torch.jit.unused.html
index 5e1b7327a7e..c69c435f74c 100644
--- a/2.9/generated/torch.jit.unused.html
+++ b/2.9/generated/torch.jit.unused.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.unused<a class="headerlink" href="#torch-jit-unused" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.unused">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">unused</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L719"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.unused" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">unused</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L719"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.unused" title="Permalink to this definition">#</a></dt>
 <dd><p>This decorator indicates to the compiler that a function or method should
 be ignored and replaced with the raising of an exception. This allows you
 to leave code in your model that is not yet TorchScript compatible and still
diff --git a/2.9/generated/torch.jit.wait.html b/2.9/generated/torch.jit.wait.html
index 47307ea8b29..4ac8b6fc16f 100644
--- a/2.9/generated/torch.jit.wait.html
+++ b/2.9/generated/torch.jit.wait.html
@@ -4404,7 +4404,7 @@
 <h1>torch.jit.wait<a class="headerlink" href="#torch-jit-wait" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.jit.wait">
-<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">future</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/jit/_async.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.wait" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.jit.</span></span><span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">future</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/jit/_async.py#L102"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.jit.wait" title="Permalink to this definition">#</a></dt>
 <dd><p>Force completion of a <cite>torch.jit.Future[T]</cite> asynchronous task, returning the result of the task.</p>
 <p>See <a class="reference internal" href="torch.jit.fork.html#torch.jit.fork" title="torch.jit.fork"><code class="xref py py-func docutils literal notranslate"><span class="pre">fork()</span></code></a> for docs and examples.
 :param future: an asynchronous task reference, created through <cite>torch.jit.fork</cite>
diff --git a/2.9/generated/torch.load.html b/2.9/generated/torch.load.html
index 442b6f4fa0a..848ed404e3c 100644
--- a/2.9/generated/torch.load.html
+++ b/2.9/generated/torch.load.html
@@ -4404,7 +4404,7 @@
 <h1>torch.load<a class="headerlink" href="#torch-load" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.load">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">pickle</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weights_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mmap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">pickle_load_args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L1271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.load" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">pickle</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weights_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mmap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">pickle_load_args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L1271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.load" title="Permalink to this definition">#</a></dt>
 <dd><p>Loads an object saved with <a class="reference internal" href="torch.save.html#torch.save" title="torch.save"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.save()</span></code></a> from a file.</p>
 <p><a class="reference internal" href="#torch.load" title="torch.load"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.load()</span></code></a> uses Python’s unpickling facilities but treats storages,
 which underlie tensors, specially. They are first deserialized on the
diff --git a/2.9/generated/torch.lobpcg.html b/2.9/generated/torch.lobpcg.html
index 80749688852..2a41ecd87e7 100644
--- a/2.9/generated/torch.lobpcg.html
+++ b/2.9/generated/torch.lobpcg.html
@@ -4404,7 +4404,7 @@
 <h1>torch.lobpcg<a class="headerlink" href="#torch-lobpcg" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.lobpcg">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">lobpcg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">A</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">B</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">X</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">iK</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">niter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">largest</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracker</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ortho_iparams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ortho_fparams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ortho_bparams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_lobpcg.py#L345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.lobpcg" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">lobpcg</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">A</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">B</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">X</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">iK</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">niter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">largest</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tracker</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ortho_iparams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ortho_fparams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ortho_bparams</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_lobpcg.py#L345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.lobpcg" title="Permalink to this definition">#</a></dt>
 <dd><p>Find the k largest (or smallest) eigenvalues and the corresponding
 eigenvectors of a symmetric positive definite generalized
 eigenvalue problem using matrix-free LOBPCG methods.</p>
diff --git a/2.9/generated/torch.lu.html b/2.9/generated/torch.lu.html
index 4336ede7936..377e213c4ab 100644
--- a/2.9/generated/torch.lu.html
+++ b/2.9/generated/torch.lu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.lu<a class="headerlink" href="#torch-lu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.lu">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">lu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.lu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">lu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.lu" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the LU factorization of a matrix or batches of matrices
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">A</span></code>. Returns a tuple containing the LU factorization and
 pivots of <code class="xref py py-attr docutils literal notranslate"><span class="pre">A</span></code>.  Pivoting is done if <code class="xref py py-attr docutils literal notranslate"><span class="pre">pivot</span></code> is set to
diff --git a/2.9/generated/torch.manual_seed.html b/2.9/generated/torch.manual_seed.html
index 15792d2ed3a..82a1d030095 100644
--- a/2.9/generated/torch.manual_seed.html
+++ b/2.9/generated/torch.manual_seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.manual_seed<a class="headerlink" href="#torch-manual-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.manual_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.manual_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.manual_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the seed for generating random numbers on all devices. Returns a
 <cite>torch.Generator</cite> object.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.meshgrid.html b/2.9/generated/torch.meshgrid.html
index acb551746e4..a6705c70d35 100644
--- a/2.9/generated/torch.meshgrid.html
+++ b/2.9/generated/torch.meshgrid.html
@@ -4404,7 +4404,7 @@
 <h1>torch.meshgrid<a class="headerlink" href="#torch-meshgrid" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.meshgrid">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">meshgrid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indexing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L396"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.meshgrid" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">meshgrid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indexing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L396"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.meshgrid" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates grids of coordinates specified by the 1D inputs in <cite>attr</cite>:tensors.</p>
 <p>This is helpful when you want to visualize data over some
 range of inputs. See below for a plotting example.</p>
diff --git a/2.9/generated/torch.mps.compile_shader.html b/2.9/generated/torch.mps.compile_shader.html
index 0fce7560a7b..ee45f528f70 100644
--- a/2.9/generated/torch.mps.compile_shader.html
+++ b/2.9/generated/torch.mps.compile_shader.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.compile_shader<a class="headerlink" href="#torch-mps-compile-shader" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.compile_shader">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">compile_shader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.compile_shader" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">compile_shader</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.compile_shader" title="Permalink to this definition">#</a></dt>
 <dd><p>Compiles compute shader from source and allows one to invoke kernels
 defined there from the comfort of Python runtime
 Example:</p>
diff --git a/2.9/generated/torch.mps.current_allocated_memory.html b/2.9/generated/torch.mps.current_allocated_memory.html
index 2a210d81350..6a4d6939d89 100644
--- a/2.9/generated/torch.mps.current_allocated_memory.html
+++ b/2.9/generated/torch.mps.current_allocated_memory.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.current_allocated_memory<a class="headerlink" href="#torch-mps-current-allocated-memory" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.current_allocated_memory">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">current_allocated_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L114"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.current_allocated_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">current_allocated_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L114"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.current_allocated_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the current GPU memory occupied by tensors in bytes.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.mps.device_count.html b/2.9/generated/torch.mps.device_count.html
index e80b949be4b..dc5bc9fa8bc 100644
--- a/2.9/generated/torch.mps.device_count.html
+++ b/2.9/generated/torch.mps.device_count.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.device_count<a class="headerlink" href="#torch-mps-device-count" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.device_count">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.device_count" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.device_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the number of available MPS devices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.mps.driver_allocated_memory.html b/2.9/generated/torch.mps.driver_allocated_memory.html
index 39c5f012ef2..dcce886b2da 100644
--- a/2.9/generated/torch.mps.driver_allocated_memory.html
+++ b/2.9/generated/torch.mps.driver_allocated_memory.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.driver_allocated_memory<a class="headerlink" href="#torch-mps-driver-allocated-memory" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.driver_allocated_memory">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">driver_allocated_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.driver_allocated_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">driver_allocated_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.driver_allocated_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns total GPU memory allocated by Metal driver for the process in bytes.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.mps.empty_cache.html b/2.9/generated/torch.mps.empty_cache.html
index fcd48f9d1d5..e783ef1f105 100644
--- a/2.9/generated/torch.mps.empty_cache.html
+++ b/2.9/generated/torch.mps.empty_cache.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.empty_cache<a class="headerlink" href="#torch-mps-empty-cache" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.empty_cache">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.empty_cache" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.empty_cache" title="Permalink to this definition">#</a></dt>
 <dd><p>Releases all unoccupied cached memory currently held by the caching
 allocator so that those can be used in other GPU applications.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.mps.event.Event.html b/2.9/generated/torch.mps.event.Event.html
index 95d89fd4afb..13777750f3f 100644
--- a/2.9/generated/torch.mps.event.Event.html
+++ b/2.9/generated/torch.mps.event.Event.html
@@ -4404,7 +4404,7 @@
 <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.mps.event.Event">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.mps.event.</span></span><span class="sig-name descname"><span class="pre">Event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable_timing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/event.py#L4"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.mps.event.</span></span><span class="sig-name descname"><span class="pre">Event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable_timing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/event.py#L4"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around an MPS event.</p>
 <p>MPS events are synchronization markers that can be used to monitor the
 device’s progress, to accurately measure timing, and to synchronize MPS streams.</p>
@@ -4416,7 +4416,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.mps.event.Event.elapsed_time">
-<span class="sig-name descname"><span class="pre">elapsed_time</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">end_event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/event.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.elapsed_time" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">elapsed_time</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">end_event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/event.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.elapsed_time" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the time elapsed in milliseconds after the event was
 recorded and before the end_event was recorded.</p>
 <dl class="field-list simple">
@@ -4428,7 +4428,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.mps.event.Event.query">
-<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/event.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.query" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/event.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.query" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if all work currently captured by event has completed.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4439,7 +4439,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.mps.event.Event.record">
-<span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/event.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.record" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/event.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.record" title="Permalink to this definition">#</a></dt>
 <dd><p>Records the event in the default stream.</p>
 <dl class="field-list simple">
 </dl>
@@ -4447,7 +4447,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.mps.event.Event.synchronize">
-<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/event.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/event.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Waits until the completion of all work currently captured in this event.
 This prevents the CPU thread from proceeding until the event completes.</p>
 <dl class="field-list simple">
@@ -4456,7 +4456,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.mps.event.Event.wait">
-<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/event.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.wait" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/event.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.event.Event.wait" title="Permalink to this definition">#</a></dt>
 <dd><p>Makes all future work submitted to the default stream wait for this event.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.mps.get_rng_state.html b/2.9/generated/torch.mps.get_rng_state.html
index 000ca2de3ee..25479c52e8f 100644
--- a/2.9/generated/torch.mps.get_rng_state.html
+++ b/2.9/generated/torch.mps.get_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.get_rng_state<a class="headerlink" href="#torch-mps-get-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.get_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mps'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.get_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mps'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.get_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the random number generator state as a ByteTensor.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mps.manual_seed.html b/2.9/generated/torch.mps.manual_seed.html
index a23069730ee..3c9dbaa7596 100644
--- a/2.9/generated/torch.mps.manual_seed.html
+++ b/2.9/generated/torch.mps.manual_seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.manual_seed<a class="headerlink" href="#torch-mps-manual-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.manual_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.manual_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.manual_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the seed for generating random numbers.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mps.profiler.is_capturing_metal.html b/2.9/generated/torch.mps.profiler.is_capturing_metal.html
index 9a255de484a..19a96452964 100644
--- a/2.9/generated/torch.mps.profiler.is_capturing_metal.html
+++ b/2.9/generated/torch.mps.profiler.is_capturing_metal.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.profiler.is_capturing_metal<a class="headerlink" href="#torch-mps-profiler-is-capturing-metal" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.profiler.is_capturing_metal">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">is_capturing_metal</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/profiler.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.is_capturing_metal" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">is_capturing_metal</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/profiler.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.is_capturing_metal" title="Permalink to this definition">#</a></dt>
 <dd><p>Checks if metal capture is in progress</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.mps.profiler.is_metal_capture_enabled.html b/2.9/generated/torch.mps.profiler.is_metal_capture_enabled.html
index fc2ce10a8f4..aee000ebd8c 100644
--- a/2.9/generated/torch.mps.profiler.is_metal_capture_enabled.html
+++ b/2.9/generated/torch.mps.profiler.is_metal_capture_enabled.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.profiler.is_metal_capture_enabled<a class="headerlink" href="#torch-mps-profiler-is-metal-capture-enabled" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.profiler.is_metal_capture_enabled">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">is_metal_capture_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/profiler.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.is_metal_capture_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">is_metal_capture_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/profiler.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.is_metal_capture_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Checks if <cite>metal_capture</cite> context manager is usable
 To enable metal capture, set MTL_CAPTURE_ENABLED envvar</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.mps.profiler.metal_capture.html b/2.9/generated/torch.mps.profiler.metal_capture.html
index c66a433a0fb..c0946cf4a71 100644
--- a/2.9/generated/torch.mps.profiler.metal_capture.html
+++ b/2.9/generated/torch.mps.profiler.metal_capture.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.profiler.metal_capture<a class="headerlink" href="#torch-mps-profiler-metal-capture" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.profiler.metal_capture">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">metal_capture</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fname</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/profiler.py#L83"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.metal_capture" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">metal_capture</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fname</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/profiler.py#L83"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.metal_capture" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager that enables capturing of Metal calls into gputrace</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.mps.profiler.profile.html b/2.9/generated/torch.mps.profiler.profile.html
index 8b728529031..90187963ed3 100644
--- a/2.9/generated/torch.mps.profiler.profile.html
+++ b/2.9/generated/torch.mps.profiler.profile.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.profiler.profile<a class="headerlink" href="#torch-mps-profiler-profile" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.profiler.profile">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">profile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'interval'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wait_until_completed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/profiler.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.profile" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">profile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'interval'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wait_until_completed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/profiler.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.profile" title="Permalink to this definition">#</a></dt>
 <dd><p>Context Manager to enabling generating OS Signpost tracing from MPS backend.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mps.profiler.start.html b/2.9/generated/torch.mps.profiler.start.html
index 707858f6443..2ffa146d492 100644
--- a/2.9/generated/torch.mps.profiler.start.html
+++ b/2.9/generated/torch.mps.profiler.start.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.profiler.start<a class="headerlink" href="#torch-mps-profiler-start" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.profiler.start">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">start</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'interval'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wait_until_completed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/profiler.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.start" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">start</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'interval'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wait_until_completed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/profiler.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.start" title="Permalink to this definition">#</a></dt>
 <dd><p>Start OS Signpost tracing from MPS backend.</p>
 <p>The generated OS Signposts could be recorded and viewed in
 XCode Instruments Logging tool.</p>
diff --git a/2.9/generated/torch.mps.profiler.stop.html b/2.9/generated/torch.mps.profiler.stop.html
index 1345180c8ee..edf80138d75 100644
--- a/2.9/generated/torch.mps.profiler.stop.html
+++ b/2.9/generated/torch.mps.profiler.stop.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.profiler.stop<a class="headerlink" href="#torch-mps-profiler-stop" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.profiler.stop">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">stop</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/profiler.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.stop" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.profiler.</span></span><span class="sig-name descname"><span class="pre">stop</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/profiler.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.profiler.stop" title="Permalink to this definition">#</a></dt>
 <dd><p>Stops generating OS Signpost tracing from MPS backend.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.mps.recommended_max_memory.html b/2.9/generated/torch.mps.recommended_max_memory.html
index 1552e981033..eea6e593104 100644
--- a/2.9/generated/torch.mps.recommended_max_memory.html
+++ b/2.9/generated/torch.mps.recommended_max_memory.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.recommended_max_memory<a class="headerlink" href="#torch-mps-recommended-max-memory" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.recommended_max_memory">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">recommended_max_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.recommended_max_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">recommended_max_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.recommended_max_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns recommended max Working set size for GPU memory in bytes.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.mps.seed.html b/2.9/generated/torch.mps.seed.html
index f23b3af25a2..e7cd919cd36 100644
--- a/2.9/generated/torch.mps.seed.html
+++ b/2.9/generated/torch.mps.seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.seed<a class="headerlink" href="#torch-mps-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.seed">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the seed for generating random numbers to a random number.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.mps.set_per_process_memory_fraction.html b/2.9/generated/torch.mps.set_per_process_memory_fraction.html
index 86a5f3bf48f..50d95f88f65 100644
--- a/2.9/generated/torch.mps.set_per_process_memory_fraction.html
+++ b/2.9/generated/torch.mps.set_per_process_memory_fraction.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.set_per_process_memory_fraction<a class="headerlink" href="#torch-mps-set-per-process-memory-fraction" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.set_per_process_memory_fraction">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">set_per_process_memory_fraction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fraction</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.set_per_process_memory_fraction" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">set_per_process_memory_fraction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fraction</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.set_per_process_memory_fraction" title="Permalink to this definition">#</a></dt>
 <dd><p>Set memory fraction for limiting process’s memory allocation on MPS device.
 The allowed value equals the fraction multiplied by recommended maximum device memory
 (obtained from Metal API device.recommendedMaxWorkingSetSize).
diff --git a/2.9/generated/torch.mps.set_rng_state.html b/2.9/generated/torch.mps.set_rng_state.html
index eb4d87b9870..41ff29d1d36 100644
--- a/2.9/generated/torch.mps.set_rng_state.html
+++ b/2.9/generated/torch.mps.set_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.set_rng_state<a class="headerlink" href="#torch-mps-set-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.set_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mps'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.set_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mps'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.set_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the random number generator state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mps.synchronize.html b/2.9/generated/torch.mps.synchronize.html
index 9712418394c..bb02c2131ab 100644
--- a/2.9/generated/torch.mps.synchronize.html
+++ b/2.9/generated/torch.mps.synchronize.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mps.synchronize<a class="headerlink" href="#torch-mps-synchronize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mps.synchronize">
-<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mps/__init__.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mps.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mps/__init__.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mps.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Waits for all kernels in all streams on a MPS device to complete.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.mtia.DeferredMtiaCallError.html b/2.9/generated/torch.mtia.DeferredMtiaCallError.html
index 71659c47537..49fbbe555b0 100644
--- a/2.9/generated/torch.mtia.DeferredMtiaCallError.html
+++ b/2.9/generated/torch.mtia.DeferredMtiaCallError.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.DeferredMtiaCallError<a class="headerlink" href="#torch-mtia-deferredmtiacallerror" title="Permalink to this heading">#</a></h1>
 <dl class="py exception">
 <dt class="sig sig-object py" id="torch.mtia.DeferredMtiaCallError">
-<em class="property"><span class="pre">exception</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">DeferredMtiaCallError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.DeferredMtiaCallError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">exception</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">DeferredMtiaCallError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.DeferredMtiaCallError" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
diff --git a/2.9/generated/torch.mtia.StreamContext.html b/2.9/generated/torch.mtia.StreamContext.html
index 0a084bd07fa..f512aa53a4e 100644
--- a/2.9/generated/torch.mtia.StreamContext.html
+++ b/2.9/generated/torch.mtia.StreamContext.html
@@ -4404,7 +4404,7 @@
 <h1>StreamContext<a class="headerlink" href="#streamcontext" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.mtia.StreamContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">StreamContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L284"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.StreamContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">StreamContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L284"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.StreamContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that selects a given stream.</p>
 <p>All MTIA kernels queued within its context will be enqueued on a selected
 stream.</p>
diff --git a/2.9/generated/torch.mtia.attach_out_of_memory_observer.html b/2.9/generated/torch.mtia.attach_out_of_memory_observer.html
index 6bb69d6158c..0801cffcbd8 100644
--- a/2.9/generated/torch.mtia.attach_out_of_memory_observer.html
+++ b/2.9/generated/torch.mtia.attach_out_of_memory_observer.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.attach_out_of_memory_observer<a class="headerlink" href="#torch-mtia-attach-out-of-memory-observer" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.attach_out_of_memory_observer">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">attach_out_of_memory_observer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L200"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.attach_out_of_memory_observer" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">attach_out_of_memory_observer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">observer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L200"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.attach_out_of_memory_observer" title="Permalink to this definition">#</a></dt>
 <dd><p>Attach an out-of-memory observer to MTIA memory allocator</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.mtia.current_device.html b/2.9/generated/torch.mtia.current_device.html
index 0c3112f5924..24e373f0367 100644
--- a/2.9/generated/torch.mtia.current_device.html
+++ b/2.9/generated/torch.mtia.current_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.current_device<a class="headerlink" href="#torch-mtia-current-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.current_device">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">current_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.current_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">current_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.current_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the index of a currently selected device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.mtia.current_stream.html b/2.9/generated/torch.mtia.current_stream.html
index b202cfd237c..ad5193c172c 100644
--- a/2.9/generated/torch.mtia.current_stream.html
+++ b/2.9/generated/torch.mtia.current_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.current_stream<a class="headerlink" href="#torch-mtia-current-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.current_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.current_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L151"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.current_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the currently selected <a class="reference internal" href="torch.mtia.Stream.html#torch.mtia.Stream" title="torch.mtia.Stream"><code class="xref py py-class docutils literal notranslate"><span class="pre">Stream</span></code></a> for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.default_stream.html b/2.9/generated/torch.mtia.default_stream.html
index 06eb79237b5..68688558b1d 100644
--- a/2.9/generated/torch.mtia.default_stream.html
+++ b/2.9/generated/torch.mtia.default_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.default_stream<a class="headerlink" href="#torch-mtia-default-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.default_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">default_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.default_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">default_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.default_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the default <a class="reference internal" href="torch.mtia.Stream.html#torch.mtia.Stream" title="torch.mtia.Stream"><code class="xref py py-class docutils literal notranslate"><span class="pre">Stream</span></code></a> for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.device.html b/2.9/generated/torch.mtia.device.html
index 205dc7fda07..3886235e179 100644
--- a/2.9/generated/torch.mtia.device.html
+++ b/2.9/generated/torch.mtia.device.html
@@ -4404,7 +4404,7 @@
 <h1>device<a class="headerlink" href="#device" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.mtia.device">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L264"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.device" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L264"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.device" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that changes the selected device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.device_count.html b/2.9/generated/torch.mtia.device_count.html
index 58db148a317..cafe3c62c5a 100644
--- a/2.9/generated/torch.mtia.device_count.html
+++ b/2.9/generated/torch.mtia.device_count.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.device_count<a class="headerlink" href="#torch-mtia-device-count" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.device_count">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.device_count" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.device_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the number of MTIA devices available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.mtia.empty_cache.html b/2.9/generated/torch.mtia.empty_cache.html
index c8b0428149b..336c88cc0bd 100644
--- a/2.9/generated/torch.mtia.empty_cache.html
+++ b/2.9/generated/torch.mtia.empty_cache.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.empty_cache<a class="headerlink" href="#torch-mtia-empty-cache" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.empty_cache">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L222"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.empty_cache" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L222"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.empty_cache" title="Permalink to this definition">#</a></dt>
 <dd><p>Empty the MTIA device cache.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.mtia.get_device_capability.html b/2.9/generated/torch.mtia.get_device_capability.html
index 37dd3cccb38..1ef47803079 100644
--- a/2.9/generated/torch.mtia.get_device_capability.html
+++ b/2.9/generated/torch.mtia.get_device_capability.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.get_device_capability<a class="headerlink" href="#torch-mtia-get-device-capability" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.get_device_capability">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">get_device_capability</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L211"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.get_device_capability" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">get_device_capability</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L211"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.get_device_capability" title="Permalink to this definition">#</a></dt>
 <dd><p>Return capability of a given device as a tuple of (major version, minor version).</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.get_rng_state.html b/2.9/generated/torch.mtia.get_rng_state.html
index dba0e23a6c6..935f13de470 100644
--- a/2.9/generated/torch.mtia.get_rng_state.html
+++ b/2.9/generated/torch.mtia.get_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.get_rng_state<a class="headerlink" href="#torch-mtia-get-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.get_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mtia'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L364"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.get_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mtia'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L364"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.get_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the random number generator state as a ByteTensor.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.init.html b/2.9/generated/torch.mtia.init.html
index afb99aa473c..1b63f1d828e 100644
--- a/2.9/generated/torch.mtia.init.html
+++ b/2.9/generated/torch.mtia.init.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.init<a class="headerlink" href="#torch-mtia-init" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.init">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">init</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.init" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">init</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.init" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
diff --git a/2.9/generated/torch.mtia.is_available.html b/2.9/generated/torch.mtia.is_available.html
index bb631c81d1a..f969311ea77 100644
--- a/2.9/generated/torch.mtia.is_available.html
+++ b/2.9/generated/torch.mtia.is_available.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.is_available<a class="headerlink" href="#torch-mtia-is-available" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return true if MTIA device is available</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.mtia.is_initialized.html b/2.9/generated/torch.mtia.is_initialized.html
index 81c0f58f150..28e92e56f73 100644
--- a/2.9/generated/torch.mtia.is_initialized.html
+++ b/2.9/generated/torch.mtia.is_initialized.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.is_initialized<a class="headerlink" href="#torch-mtia-is-initialized" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.is_initialized">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">is_initialized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.is_initialized" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">is_initialized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.is_initialized" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether PyTorch’s MTIA state has been initialized.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.mtia.memory.memory_allocated.html b/2.9/generated/torch.mtia.memory.memory_allocated.html
index 8f6d48c8083..3756043dc27 100644
--- a/2.9/generated/torch.mtia.memory.memory_allocated.html
+++ b/2.9/generated/torch.mtia.memory.memory_allocated.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.memory.memory_allocated<a class="headerlink" href="#torch-mtia-memory-memory-allocated" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.memory.memory_allocated">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.memory.</span></span><span class="sig-name descname"><span class="pre">memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/memory.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.memory.memory_allocated" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.memory.</span></span><span class="sig-name descname"><span class="pre">memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/memory.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.memory.memory_allocated" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current MTIA memory occupied by tensors in bytes for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.memory.memory_stats.html b/2.9/generated/torch.mtia.memory.memory_stats.html
index 66b8456058b..d41a7e8d01e 100644
--- a/2.9/generated/torch.mtia.memory.memory_stats.html
+++ b/2.9/generated/torch.mtia.memory.memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.memory.memory_stats<a class="headerlink" href="#torch-mtia-memory-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.memory.memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/memory.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.memory.memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/memory.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.memory.memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary of MTIA memory allocator statistics for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.memory_stats.html b/2.9/generated/torch.mtia.memory_stats.html
index bb931969e53..af35a12ab57 100644
--- a/2.9/generated/torch.mtia.memory_stats.html
+++ b/2.9/generated/torch.mtia.memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.memory_stats<a class="headerlink" href="#torch-mtia-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/memory.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/memory.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary of MTIA memory allocator statistics for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.record_memory_history.html b/2.9/generated/torch.mtia.record_memory_history.html
index 2e7591c5dc1..24b38ff40f6 100644
--- a/2.9/generated/torch.mtia.record_memory_history.html
+++ b/2.9/generated/torch.mtia.record_memory_history.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.record_memory_history<a class="headerlink" href="#torch-mtia-record-memory-history" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.record_memory_history">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">record_memory_history</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stacks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'python'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_entries</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.record_memory_history" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">record_memory_history</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stacks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'python'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_entries</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.record_memory_history" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable/Disable the memory profiler on MTIA allocator</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.set_device.html b/2.9/generated/torch.mtia.set_device.html
index 18466225053..ff00f2b7536 100644
--- a/2.9/generated/torch.mtia.set_device.html
+++ b/2.9/generated/torch.mtia.set_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.set_device<a class="headerlink" href="#torch-mtia-set-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.set_device">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">set_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.set_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">set_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.set_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the current device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.set_rng_state.html b/2.9/generated/torch.mtia.set_rng_state.html
index 8e6bc530819..119985449e3 100644
--- a/2.9/generated/torch.mtia.set_rng_state.html
+++ b/2.9/generated/torch.mtia.set_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.set_rng_state<a class="headerlink" href="#torch-mtia-set-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.set_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mtia'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L379"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.set_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mtia'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L379"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.set_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the random number generator state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.set_stream.html b/2.9/generated/torch.mtia.set_stream.html
index 14e41b75c59..394dfbfbe3b 100644
--- a/2.9/generated/torch.mtia.set_stream.html
+++ b/2.9/generated/torch.mtia.set_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.set_stream<a class="headerlink" href="#torch-mtia-set-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.set_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">set_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.set_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">set_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.set_stream" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Set the current stream.This is a wrapper API to set the stream.</dt><dd><p>Usage of this function is discouraged in favor of the <code class="docutils literal notranslate"><span class="pre">stream</span></code>
 context manager.</p>
diff --git a/2.9/generated/torch.mtia.snapshot.html b/2.9/generated/torch.mtia.snapshot.html
index 11049ff8d2c..505298b8702 100644
--- a/2.9/generated/torch.mtia.snapshot.html
+++ b/2.9/generated/torch.mtia.snapshot.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.snapshot<a class="headerlink" href="#torch-mtia-snapshot" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.snapshot">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">snapshot</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.snapshot" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">snapshot</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.snapshot" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary of MTIA memory allocator history</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.mtia.stream.html b/2.9/generated/torch.mtia.stream.html
index 47cb1064b76..c2be92fd57f 100644
--- a/2.9/generated/torch.mtia.stream.html
+++ b/2.9/generated/torch.mtia.stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.stream<a class="headerlink" href="#torch-mtia-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.stream">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrap around the Context-manager StreamContext that selects a given stream.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.mtia.synchronize.html b/2.9/generated/torch.mtia.synchronize.html
index 9925e6b8d02..258bd2f962c 100644
--- a/2.9/generated/torch.mtia.synchronize.html
+++ b/2.9/generated/torch.mtia.synchronize.html
@@ -4404,7 +4404,7 @@
 <h1>torch.mtia.synchronize<a class="headerlink" href="#torch-mtia-synchronize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.mtia.synchronize">
-<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/mtia/__init__.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.mtia.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/mtia/__init__.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.mtia.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Waits for all jobs in all streams on a MTIA device to complete.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.AdaptiveAvgPool1d.html b/2.9/generated/torch.nn.AdaptiveAvgPool1d.html
index d5ead0f01aa..b008a359eaa 100644
--- a/2.9/generated/torch.nn.AdaptiveAvgPool1d.html
+++ b/2.9/generated/torch.nn.AdaptiveAvgPool1d.html
@@ -4404,7 +4404,7 @@
 <h1>AdaptiveAvgPool1d<a class="headerlink" href="#adaptiveavgpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveAvgPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1432"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1432"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D adaptive average pooling over an input signal composed of several input planes.</p>
 <p>The output size is <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>L</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub></mrow><annotation encoding="application/x-tex">L_{out}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4430,7 +4430,7 @@ <h1>AdaptiveAvgPool1d<a class="headerlink" href="#adaptiveavgpool1d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveAvgPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1456"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1456"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.AdaptiveAvgPool2d.html b/2.9/generated/torch.nn.AdaptiveAvgPool2d.html
index 8096e39c63e..9af4550940c 100644
--- a/2.9/generated/torch.nn.AdaptiveAvgPool2d.html
+++ b/2.9/generated/torch.nn.AdaptiveAvgPool2d.html
@@ -4404,7 +4404,7 @@
 <h1>AdaptiveAvgPool2d<a class="headerlink" href="#adaptiveavgpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveAvgPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1463"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1463"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D adaptive average pooling over an input signal composed of several input planes.</p>
 <p>The output is of size H x W, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4441,7 +4441,7 @@ <h1>AdaptiveAvgPool2d<a class="headerlink" href="#adaptiveavgpool2d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveAvgPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.AdaptiveAvgPool3d.html b/2.9/generated/torch.nn.AdaptiveAvgPool3d.html
index 74725ab2b7c..f7b3060475b 100644
--- a/2.9/generated/torch.nn.AdaptiveAvgPool3d.html
+++ b/2.9/generated/torch.nn.AdaptiveAvgPool3d.html
@@ -4404,7 +4404,7 @@
 <h1>AdaptiveAvgPool3d<a class="headerlink" href="#adaptiveavgpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveAvgPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1503"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1503"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D adaptive average pooling over an input signal composed of several input planes.</p>
 <p>The output is of size D x H x W, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4441,7 +4441,7 @@ <h1>AdaptiveAvgPool3d<a class="headerlink" href="#adaptiveavgpool3d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveAvgPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveAvgPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.AdaptiveLogSoftmaxWithLoss.html b/2.9/generated/torch.nn.AdaptiveLogSoftmaxWithLoss.html
index 9646ca0fc59..0e38c7fad17 100644
--- a/2.9/generated/torch.nn.AdaptiveLogSoftmaxWithLoss.html
+++ b/2.9/generated/torch.nn.AdaptiveLogSoftmaxWithLoss.html
@@ -4404,7 +4404,7 @@
 <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwithloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveLogSoftmaxWithLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveLogSoftmaxWithLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cutoffs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">div_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">head_bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveLogSoftmaxWithLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cutoffs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">div_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">head_bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Efficient softmax approximation.</p>
 <p>As described in
 <a class="reference external" href="https://arxiv.org/abs/1609.04309">Efficient softmax approximation for GPUs by Edouard Grave, Armand Joulin,
@@ -4498,7 +4498,7 @@ <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwit
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveLogSoftmaxWithLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4509,7 +4509,7 @@ <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwit
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveLogSoftmaxWithLoss.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss.log_prob" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute log probabilities for all <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext mathvariant="monospace">n_classes</mtext></mrow><annotation encoding="application/x-tex">\texttt{n\_classes}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7063em;vertical-align:-0.0951em;"></span><span class="mord text"><span class="mord texttt">n_classes</span></span></span></span></span></span>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4535,7 +4535,7 @@ <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwit
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveLogSoftmaxWithLoss.predict">
-<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss.predict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss.predict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the class with the highest probability for each example in the input minibatch.</p>
 <p>This is equivalent to <code class="docutils literal notranslate"><span class="pre">self.log_prob(input).argmax(dim=1)</span></code>, but is more efficient in some cases.</p>
 <dl class="field-list simple">
@@ -4560,7 +4560,7 @@ <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwit
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveLogSoftmaxWithLoss.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveLogSoftmaxWithLoss.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.AdaptiveMaxPool1d.html b/2.9/generated/torch.nn.AdaptiveMaxPool1d.html
index 8a532a477e7..2400d7dd6dd 100644
--- a/2.9/generated/torch.nn.AdaptiveMaxPool1d.html
+++ b/2.9/generated/torch.nn.AdaptiveMaxPool1d.html
@@ -4404,7 +4404,7 @@
 <h1>AdaptiveMaxPool1d<a class="headerlink" href="#adaptivemaxpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveMaxPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D adaptive max pooling over an input signal composed of several input planes.</p>
 <p>The output size is <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>L</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub></mrow><annotation encoding="application/x-tex">L_{out}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4434,7 +4434,7 @@ <h1>AdaptiveMaxPool1d<a class="headerlink" href="#adaptivemaxpool1d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveMaxPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1329"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1329"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.AdaptiveMaxPool2d.html b/2.9/generated/torch.nn.AdaptiveMaxPool2d.html
index 59fcad1fd1f..f6171330e20 100644
--- a/2.9/generated/torch.nn.AdaptiveMaxPool2d.html
+++ b/2.9/generated/torch.nn.AdaptiveMaxPool2d.html
@@ -4404,7 +4404,7 @@
 <h1>AdaptiveMaxPool2d<a class="headerlink" href="#adaptivemaxpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveMaxPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D adaptive max pooling over an input signal composed of several input planes.</p>
 <p>The output is of size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo>×</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub></mrow><annotation encoding="application/x-tex">H_{out} \times W_{out}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4446,7 +4446,7 @@ <h1>AdaptiveMaxPool2d<a class="headerlink" href="#adaptivemaxpool2d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveMaxPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1372"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1372"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.AdaptiveMaxPool3d.html b/2.9/generated/torch.nn.AdaptiveMaxPool3d.html
index 6ac3053eb49..ed7ec531ba5 100644
--- a/2.9/generated/torch.nn.AdaptiveMaxPool3d.html
+++ b/2.9/generated/torch.nn.AdaptiveMaxPool3d.html
@@ -4404,7 +4404,7 @@
 <h1>AdaptiveMaxPool3d<a class="headerlink" href="#adaptivemaxpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveMaxPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D adaptive max pooling over an input signal composed of several input planes.</p>
 <p>The output is of size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>D</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo>×</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo>×</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub></mrow><annotation encoding="application/x-tex">D_{out} \times H_{out} \times W_{out}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4446,7 +4446,7 @@ <h1>AdaptiveMaxPool3d<a class="headerlink" href="#adaptivemaxpool3d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AdaptiveMaxPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AdaptiveMaxPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.AlphaDropout.html b/2.9/generated/torch.nn.AlphaDropout.html
index 571546e8ddb..b4da11e7c67 100644
--- a/2.9/generated/torch.nn.AlphaDropout.html
+++ b/2.9/generated/torch.nn.AlphaDropout.html
@@ -4404,7 +4404,7 @@
 <h1>AlphaDropout<a class="headerlink" href="#alphadropout" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AlphaDropout">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AlphaDropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AlphaDropout" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AlphaDropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AlphaDropout" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Alpha Dropout over the input.</p>
 <p>Alpha Dropout is a type of Dropout that maintains the self-normalizing
 property.
@@ -4443,7 +4443,7 @@ <h1>AlphaDropout<a class="headerlink" href="#alphadropout" title="Permalink to t
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AlphaDropout.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AlphaDropout.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AlphaDropout.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.AvgPool1d.html b/2.9/generated/torch.nn.AvgPool1d.html
index 176567ef298..7a62245989a 100644
--- a/2.9/generated/torch.nn.AvgPool1d.html
+++ b/2.9/generated/torch.nn.AvgPool1d.html
@@ -4404,7 +4404,7 @@
 <h1>AvgPool1d<a class="headerlink" href="#avgpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AvgPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AvgPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AvgPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D average pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>L</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, L)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">L</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>L</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, L_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi></mrow><annotation encoding="application/x-tex">k</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span></span></span></span></span>
@@ -4459,7 +4459,7 @@ <h1>AvgPool1d<a class="headerlink" href="#avgpool1d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AvgPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L670"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L670"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.AvgPool2d.html b/2.9/generated/torch.nn.AvgPool2d.html
index 8431ef54e82..15c12581c67 100644
--- a/2.9/generated/torch.nn.AvgPool2d.html
+++ b/2.9/generated/torch.nn.AvgPool2d.html
@@ -4404,7 +4404,7 @@
 <h1>AvgPool2d<a class="headerlink" href="#avgpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AvgPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AvgPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L682"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AvgPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L682"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D average pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, H_{out}, W_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>k</mi><mi>H</mi><mo separator="true">,</mo><mi>k</mi><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(kH, kW)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span><span class="mclose">)</span></span></span></span></span>
@@ -4473,7 +4473,7 @@ <h1>AvgPool2d<a class="headerlink" href="#avgpool2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AvgPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L779"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L779"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.AvgPool3d.html b/2.9/generated/torch.nn.AvgPool3d.html
index 16270a83d2b..58abd9605c5 100644
--- a/2.9/generated/torch.nn.AvgPool3d.html
+++ b/2.9/generated/torch.nn.AvgPool3d.html
@@ -4404,7 +4404,7 @@
 <h1>AvgPool3d<a class="headerlink" href="#avgpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.AvgPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AvgPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L792"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">AvgPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L792"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D average pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>D</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, D, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>D</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, D_{out}, H_{out}, W_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>k</mi><mi>D</mi><mo separator="true">,</mo><mi>k</mi><mi>H</mi><mo separator="true">,</mo><mi>k</mi><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(kD, kH, kW)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span><span class="mclose">)</span></span></span></span></span>
@@ -4484,7 +4484,7 @@ <h1>AvgPool3d<a class="headerlink" href="#avgpool3d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.AvgPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L896"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L896"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.AvgPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.BCELoss.html b/2.9/generated/torch.nn.BCELoss.html
index 3d681d1ba50..63cad042008 100644
--- a/2.9/generated/torch.nn.BCELoss.html
+++ b/2.9/generated/torch.nn.BCELoss.html
@@ -4404,7 +4404,7 @@
 <h1>BCELoss<a class="headerlink" href="#bceloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.BCELoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BCELoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L637"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BCELoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BCELoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L637"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BCELoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the Binary Cross Entropy between the target and
 the input probabilities:</p>
 <p>The unreduced (i.e. with <code class="xref py py-attr docutils literal notranslate"><span class="pre">reduction</span></code> set to <code class="docutils literal notranslate"><span class="pre">'none'</span></code>) loss can be described as:</p>
@@ -4479,7 +4479,7 @@ <h1>BCELoss<a class="headerlink" href="#bceloss" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.BCELoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L723"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BCELoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L723"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BCELoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.BCEWithLogitsLoss.html b/2.9/generated/torch.nn.BCEWithLogitsLoss.html
index 861420f3329..40027fd3b8c 100644
--- a/2.9/generated/torch.nn.BCEWithLogitsLoss.html
+++ b/2.9/generated/torch.nn.BCEWithLogitsLoss.html
@@ -4404,7 +4404,7 @@
 <h1>BCEWithLogitsLoss<a class="headerlink" href="#bcewithlogitsloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.BCEWithLogitsLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BCEWithLogitsLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BCEWithLogitsLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BCEWithLogitsLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BCEWithLogitsLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>This loss combines a <cite>Sigmoid</cite> layer and the <cite>BCELoss</cite> in one single
 class. This version is more numerically stable than using a plain <cite>Sigmoid</cite>
 followed by a <cite>BCELoss</cite> as, by combining the operations into one layer,
@@ -4505,7 +4505,7 @@ <h1>BCEWithLogitsLoss<a class="headerlink" href="#bcewithlogitsloss" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.BCEWithLogitsLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L848"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BCEWithLogitsLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L848"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BCEWithLogitsLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.BatchNorm1d.html b/2.9/generated/torch.nn.BatchNorm1d.html
index f90b694f505..eebdf4878d6 100644
--- a/2.9/generated/torch.nn.BatchNorm1d.html
+++ b/2.9/generated/torch.nn.BatchNorm1d.html
@@ -4404,7 +4404,7 @@
 <h1>BatchNorm1d<a class="headerlink" href="#batchnorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.BatchNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BatchNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BatchNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BatchNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BatchNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Batch Normalization over a 2D or 3D input.</p>
 <p>Method described in the paper
 <a class="reference external" href="https://arxiv.org/abs/1502.03167">Batch Normalization: Accelerating Deep Network Training by Reducing
diff --git a/2.9/generated/torch.nn.BatchNorm2d.html b/2.9/generated/torch.nn.BatchNorm2d.html
index 18c62905d76..f58b15c5009 100644
--- a/2.9/generated/torch.nn.BatchNorm2d.html
+++ b/2.9/generated/torch.nn.BatchNorm2d.html
@@ -4404,7 +4404,7 @@
 <h1>BatchNorm2d<a class="headerlink" href="#batchnorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.BatchNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BatchNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BatchNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Batch Normalization over a 4D input.</p>
 <p>4D is a mini-batch of 2D inputs
 with additional channel dimension. Method described in the paper
diff --git a/2.9/generated/torch.nn.BatchNorm3d.html b/2.9/generated/torch.nn.BatchNorm3d.html
index 08f04e817eb..f7677e7db97 100644
--- a/2.9/generated/torch.nn.BatchNorm3d.html
+++ b/2.9/generated/torch.nn.BatchNorm3d.html
@@ -4404,7 +4404,7 @@
 <h1>BatchNorm3d<a class="headerlink" href="#batchnorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.BatchNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L491"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BatchNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">BatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L491"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.BatchNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Batch Normalization over a 5D input.</p>
 <p>5D is a mini-batch of 3D inputs with additional channel dimension as described in the paper
 <a class="reference external" href="https://arxiv.org/abs/1502.03167">Batch Normalization: Accelerating Deep Network Training by Reducing
diff --git a/2.9/generated/torch.nn.Bilinear.html b/2.9/generated/torch.nn.Bilinear.html
index 2c91b1bf150..150fbc9b333 100644
--- a/2.9/generated/torch.nn.Bilinear.html
+++ b/2.9/generated/torch.nn.Bilinear.html
@@ -4404,7 +4404,7 @@
 <h1>Bilinear<a class="headerlink" href="#bilinear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Bilinear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Bilinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in1_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in2_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Bilinear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Bilinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in1_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in2_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Bilinear" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a bilinear transformation to the incoming data: <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><msubsup><mi>x</mi><mn>1</mn><mi>T</mi></msubsup><mi>A</mi><msub><mi>x</mi><mn>2</mn></msub><mo>+</mo><mi>b</mi></mrow><annotation encoding="application/x-tex">y = x_1^T A x_2 + b</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.0894em;vertical-align:-0.2481em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8413em;"><span style="top:-2.4519em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight" style="margin-right:0.13889em;">T</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2481em;"><span></span></span></span></span></span></span><span class="mord mathnormal">A</span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal">b</span></span></span></span></span>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4497,7 +4497,7 @@ <h1>Bilinear<a class="headerlink" href="#bilinear" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Bilinear.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L247"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Bilinear.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L247"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Bilinear.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4508,7 +4508,7 @@ <h1>Bilinear<a class="headerlink" href="#bilinear" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Bilinear.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Bilinear.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Bilinear.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4519,7 +4519,7 @@ <h1>Bilinear<a class="headerlink" href="#bilinear" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Bilinear.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L232"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Bilinear.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L232"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Bilinear.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.CELU.html b/2.9/generated/torch.nn.CELU.html
index ac87e5722d0..25ffbaa5b1e 100644
--- a/2.9/generated/torch.nn.CELU.html
+++ b/2.9/generated/torch.nn.CELU.html
@@ -4404,7 +4404,7 @@
 <h1>CELU<a class="headerlink" href="#celu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.CELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CELU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the CELU function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>CELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>α</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mi mathvariant="normal">/</mi><mi>α</mi><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{CELU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1))
@@ -4434,7 +4434,7 @@ <h1>CELU<a class="headerlink" href="#celu" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.CELU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L670"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CELU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L670"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CELU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4445,7 +4445,7 @@ <h1>CELU<a class="headerlink" href="#celu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.CELU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L664"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CELU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L664"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CELU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.CTCLoss.html b/2.9/generated/torch.nn.CTCLoss.html
index f36ba7a89af..b2bd1973562 100644
--- a/2.9/generated/torch.nn.CTCLoss.html
+++ b/2.9/generated/torch.nn.CTCLoss.html
@@ -4404,7 +4404,7 @@
 <h1>CTCLoss<a class="headerlink" href="#ctcloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.CTCLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CTCLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">blank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_infinity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1932"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CTCLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CTCLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">blank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_infinity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1932"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CTCLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>The Connectionist Temporal Classification loss.</p>
 <p>Calculates loss between a continuous (unsegmented) time series and a target sequence. CTCLoss sums over the
 probability of possible alignments of input to target, producing a loss value which is differentiable
@@ -4559,7 +4559,7 @@ <h1>CTCLoss<a class="headerlink" href="#ctcloss" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.CTCLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_probs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">targets</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_lengths</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L2093"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CTCLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_probs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">targets</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_lengths</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L2093"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CTCLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ChannelShuffle.html b/2.9/generated/torch.nn.ChannelShuffle.html
index 0b8618b381d..3b0c9d34b2c 100644
--- a/2.9/generated/torch.nn.ChannelShuffle.html
+++ b/2.9/generated/torch.nn.ChannelShuffle.html
@@ -4404,7 +4404,7 @@
 <h1>ChannelShuffle<a class="headerlink" href="#channelshuffle" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ChannelShuffle">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ChannelShuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">groups</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/channelshuffle.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ChannelShuffle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ChannelShuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">groups</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/channelshuffle.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ChannelShuffle" title="Permalink to this definition">#</a></dt>
 <dd><p>Divides and rearranges the channels in a tensor.</p>
 <p>This operation divides the channels in a tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mo>∗</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, *)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">∗</span><span class="mclose">)</span></span></span></span></span>
 into g groups as <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mfrac><mi>C</mi><mi>g</mi></mfrac><mo separator="true">,</mo><mi>g</mi><mo separator="true">,</mo><mo>∗</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, \frac{C}{g}, g, *)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1.3534em;vertical-align:-0.4811em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8723em;"><span style="top:-2.655em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight" style="margin-right:0.03588em;">g</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.394em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight" style="margin-right:0.07153em;">C</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.4811em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">g</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">∗</span><span class="mclose">)</span></span></span></span></span> and shuffles them,
@@ -4440,7 +4440,7 @@ <h1>ChannelShuffle<a class="headerlink" href="#channelshuffle" title="Permalink
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ChannelShuffle.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/channelshuffle.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ChannelShuffle.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/channelshuffle.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ChannelShuffle.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4451,7 +4451,7 @@ <h1>ChannelShuffle<a class="headerlink" href="#channelshuffle" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ChannelShuffle.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/channelshuffle.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ChannelShuffle.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/channelshuffle.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ChannelShuffle.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.CircularPad1d.html b/2.9/generated/torch.nn.CircularPad1d.html
index c5c7bb8d24b..7a00f11cbc0 100644
--- a/2.9/generated/torch.nn.CircularPad1d.html
+++ b/2.9/generated/torch.nn.CircularPad1d.html
@@ -4404,7 +4404,7 @@
 <h1>CircularPad1d<a class="headerlink" href="#circularpad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.CircularPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CircularPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CircularPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CircularPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CircularPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using circular padding of the input boundary.</p>
 <p>Tensor values at the beginning of the dimension are used to pad the end,
 and values at the end are used to pad the beginning. If negative padding is
diff --git a/2.9/generated/torch.nn.CircularPad2d.html b/2.9/generated/torch.nn.CircularPad2d.html
index baf6c883be7..bea7ef2c46b 100644
--- a/2.9/generated/torch.nn.CircularPad2d.html
+++ b/2.9/generated/torch.nn.CircularPad2d.html
@@ -4404,7 +4404,7 @@
 <h1>CircularPad2d<a class="headerlink" href="#circularpad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.CircularPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CircularPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CircularPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CircularPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CircularPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using circular padding of the input boundary.</p>
 <p>Tensor values at the beginning of the dimension are used to pad the end,
 and values at the end are used to pad the beginning. If negative padding is
diff --git a/2.9/generated/torch.nn.CircularPad3d.html b/2.9/generated/torch.nn.CircularPad3d.html
index 0342354ee02..8194fdeceb5 100644
--- a/2.9/generated/torch.nn.CircularPad3d.html
+++ b/2.9/generated/torch.nn.CircularPad3d.html
@@ -4404,7 +4404,7 @@
 <h1>CircularPad3d<a class="headerlink" href="#circularpad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.CircularPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CircularPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CircularPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CircularPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CircularPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using circular padding of the input boundary.</p>
 <p>Tensor values at the beginning of the dimension are used to pad the end,
 and values at the end are used to pad the beginning. If negative padding is
diff --git a/2.9/generated/torch.nn.ConstantPad1d.html b/2.9/generated/torch.nn.ConstantPad1d.html
index 90268b76381..ac492e918e8 100644
--- a/2.9/generated/torch.nn.ConstantPad1d.html
+++ b/2.9/generated/torch.nn.ConstantPad1d.html
@@ -4404,7 +4404,7 @@
 <h1>ConstantPad1d<a class="headerlink" href="#constantpad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ConstantPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConstantPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConstantPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConstantPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConstantPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with a constant value.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.ConstantPad2d.html b/2.9/generated/torch.nn.ConstantPad2d.html
index 040a3e719ff..28d95029761 100644
--- a/2.9/generated/torch.nn.ConstantPad2d.html
+++ b/2.9/generated/torch.nn.ConstantPad2d.html
@@ -4404,7 +4404,7 @@
 <h1>ConstantPad2d<a class="headerlink" href="#constantpad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ConstantPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConstantPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConstantPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConstantPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConstantPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with a constant value.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.ConstantPad3d.html b/2.9/generated/torch.nn.ConstantPad3d.html
index 020ffcffb2a..0d09eba07f8 100644
--- a/2.9/generated/torch.nn.ConstantPad3d.html
+++ b/2.9/generated/torch.nn.ConstantPad3d.html
@@ -4404,7 +4404,7 @@
 <h1>ConstantPad3d<a class="headerlink" href="#constantpad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ConstantPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConstantPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConstantPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConstantPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConstantPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with a constant value.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.Conv1d.html b/2.9/generated/torch.nn.Conv1d.html
index 3106e0c856f..0b1ef8bbfcf 100644
--- a/2.9/generated/torch.nn.Conv1d.html
+++ b/2.9/generated/torch.nn.Conv1d.html
@@ -4404,7 +4404,7 @@
 <h1>Conv1d<a class="headerlink" href="#conv1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Conv1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Conv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Conv1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Conv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Conv1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D convolution over an input signal composed of several input
 planes.</p>
 <p>In the simplest case, the output value of the layer with input size
diff --git a/2.9/generated/torch.nn.Conv2d.html b/2.9/generated/torch.nn.Conv2d.html
index df860512a74..0ce1f5a7181 100644
--- a/2.9/generated/torch.nn.Conv2d.html
+++ b/2.9/generated/torch.nn.Conv2d.html
@@ -4404,7 +4404,7 @@
 <h1>Conv2d<a class="headerlink" href="#conv2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Conv2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Conv2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Conv2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D convolution over an input signal composed of several input
 planes.</p>
 <p>In the simplest case, the output value of the layer with input size
diff --git a/2.9/generated/torch.nn.Conv3d.html b/2.9/generated/torch.nn.Conv3d.html
index d20aa165fce..350e03d055d 100644
--- a/2.9/generated/torch.nn.Conv3d.html
+++ b/2.9/generated/torch.nn.Conv3d.html
@@ -4404,7 +4404,7 @@
 <h1>Conv3d<a class="headerlink" href="#conv3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Conv3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Conv3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Conv3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D convolution over an input signal composed of several input
 planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><msub><mi>C</mi><mrow><mi>i</mi><mi>n</mi></mrow></msub><mo separator="true">,</mo><mi>D</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C_{in}, D, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3117em;"><span style="top:-2.55em;margin-left:-0.0715em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">in</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>
diff --git a/2.9/generated/torch.nn.ConvTranspose1d.html b/2.9/generated/torch.nn.ConvTranspose1d.html
index 7165a0fdb6b..f400999bd28 100644
--- a/2.9/generated/torch.nn.ConvTranspose1d.html
+++ b/2.9/generated/torch.nn.ConvTranspose1d.html
@@ -4404,7 +4404,7 @@
 <h1>ConvTranspose1d<a class="headerlink" href="#convtranspose1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ConvTranspose1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConvTranspose1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConvTranspose1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D transposed convolution operator over an input image
 composed of several input planes.</p>
 <p>This module can be seen as the gradient of Conv1d with respect to its input.
diff --git a/2.9/generated/torch.nn.ConvTranspose2d.html b/2.9/generated/torch.nn.ConvTranspose2d.html
index f77268a0d5d..15bb0eca1b3 100644
--- a/2.9/generated/torch.nn.ConvTranspose2d.html
+++ b/2.9/generated/torch.nn.ConvTranspose2d.html
@@ -4404,7 +4404,7 @@
 <h1>ConvTranspose2d<a class="headerlink" href="#convtranspose2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ConvTranspose2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L976"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConvTranspose2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L976"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConvTranspose2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D transposed convolution operator over an input image
 composed of several input planes.</p>
 <p>This module can be seen as the gradient of Conv2d with respect to its input.
@@ -4582,7 +4582,7 @@ <h1>ConvTranspose2d<a class="headerlink" href="#convtranspose2d" title="Permalin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ConvTranspose2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1133"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConvTranspose2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1133"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConvTranspose2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Variables</dt>
diff --git a/2.9/generated/torch.nn.ConvTranspose3d.html b/2.9/generated/torch.nn.ConvTranspose3d.html
index fa3a5bf3dc6..d47c65fcdd4 100644
--- a/2.9/generated/torch.nn.ConvTranspose3d.html
+++ b/2.9/generated/torch.nn.ConvTranspose3d.html
@@ -4404,7 +4404,7 @@
 <h1>ConvTranspose3d<a class="headerlink" href="#convtranspose3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ConvTranspose3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConvTranspose3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ConvTranspose3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D transposed convolution operator over an input image composed of several input
 planes.
 The transposed convolution operator multiplies each input value element-wise by a learnable kernel,
diff --git a/2.9/generated/torch.nn.CosineEmbeddingLoss.html b/2.9/generated/torch.nn.CosineEmbeddingLoss.html
index 56587835b46..f80dfa065a8 100644
--- a/2.9/generated/torch.nn.CosineEmbeddingLoss.html
+++ b/2.9/generated/torch.nn.CosineEmbeddingLoss.html
@@ -4404,7 +4404,7 @@
 <h1>CosineEmbeddingLoss<a class="headerlink" href="#cosineembeddingloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.CosineEmbeddingLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CosineEmbeddingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CosineEmbeddingLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CosineEmbeddingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CosineEmbeddingLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the loss given input tensors
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>1</mn></msub></mrow><annotation encoding="application/x-tex">x_1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>2</mn></msub></mrow><annotation encoding="application/x-tex">x_2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> and a <cite>Tensor</cite> label <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> with values 1 or -1.
 Use (<span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mn>1</mn></mrow><annotation encoding="application/x-tex">y=1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord">1</span></span></span></span></span>) to maximize the cosine similarity of two inputs, and (<span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mo>−</mo><mn>1</mn></mrow><annotation encoding="application/x-tex">y=-1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.7278em;vertical-align:-0.0833em;"></span><span class="mord">−</span><span class="mord">1</span></span></span></span></span>) otherwise.
@@ -4462,7 +4462,7 @@ <h1>CosineEmbeddingLoss<a class="headerlink" href="#cosineembeddingloss" title="
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.CosineEmbeddingLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1517"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CosineEmbeddingLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1517"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CosineEmbeddingLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.CosineSimilarity.html b/2.9/generated/torch.nn.CosineSimilarity.html
index 0964f66caec..f402827c545 100644
--- a/2.9/generated/torch.nn.CosineSimilarity.html
+++ b/2.9/generated/torch.nn.CosineSimilarity.html
@@ -4404,7 +4404,7 @@
 <h1>CosineSimilarity<a class="headerlink" href="#cosinesimilarity" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.CosineSimilarity">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CosineSimilarity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/distance.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CosineSimilarity" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CosineSimilarity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/distance.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CosineSimilarity" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns cosine similarity between <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>1</mn></msub></mrow><annotation encoding="application/x-tex">x_1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>2</mn></msub></mrow><annotation encoding="application/x-tex">x_2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, computed along <cite>dim</cite>.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>similarity</mtext><mo>=</mo><mfrac><mrow><msub><mi>x</mi><mn>1</mn></msub><mo>⋅</mo><msub><mi>x</mi><mn>2</mn></msub></mrow><mrow><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi mathvariant="normal">∥</mi><msub><mi>x</mi><mn>1</mn></msub><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub><mo>⋅</mo><mi mathvariant="normal">∥</mi><msub><mi>x</mi><mn>2</mn></msub><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub><mo separator="true">,</mo><mi>ϵ</mi><mo stretchy="false">)</mo></mrow></mfrac><mi mathvariant="normal">.</mi></mrow><annotation encoding="application/x-tex">\text{similarity} = \dfrac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)}.
@@ -4436,7 +4436,7 @@ <h1>CosineSimilarity<a class="headerlink" href="#cosinesimilarity" title="Permal
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.CosineSimilarity.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/distance.py#L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CosineSimilarity.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/distance.py#L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CosineSimilarity.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.CrossEntropyLoss.html b/2.9/generated/torch.nn.CrossEntropyLoss.html
index 813d0d23b92..be0a2cd7e65 100644
--- a/2.9/generated/torch.nn.CrossEntropyLoss.html
+++ b/2.9/generated/torch.nn.CrossEntropyLoss.html
@@ -4404,7 +4404,7 @@
 <h1>CrossEntropyLoss<a class="headerlink" href="#crossentropyloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.CrossEntropyLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CrossEntropyLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label_smoothing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CrossEntropyLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">CrossEntropyLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label_smoothing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CrossEntropyLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>This criterion computes the cross entropy loss between input logits
 and target.</p>
 <p>It is useful when training a classification problem with <cite>C</cite> classes.
@@ -4587,7 +4587,7 @@ <h1>CrossEntropyLoss<a class="headerlink" href="#crossentropyloss" title="Permal
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.CrossEntropyLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CrossEntropyLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.CrossEntropyLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.DataParallel.html b/2.9/generated/torch.nn.DataParallel.html
index 75b4f406357..771fb026168 100644
--- a/2.9/generated/torch.nn.DataParallel.html
+++ b/2.9/generated/torch.nn.DataParallel.html
@@ -4404,7 +4404,7 @@
 <h1>DataParallel<a class="headerlink" href="#dataparallel" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.DataParallel">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">DataParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/data_parallel.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.DataParallel" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">DataParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/data_parallel.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.DataParallel" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements data parallelism at the module level.</p>
 <p>This container parallelizes the application of the given <code class="xref py py-attr docutils literal notranslate"><span class="pre">module</span></code> by
 splitting the input across the specified devices by chunking in the batch
diff --git a/2.9/generated/torch.nn.Dropout.html b/2.9/generated/torch.nn.Dropout.html
index 02d32146d27..547cf282d8f 100644
--- a/2.9/generated/torch.nn.Dropout.html
+++ b/2.9/generated/torch.nn.Dropout.html
@@ -4404,7 +4404,7 @@
 <h1>Dropout<a class="headerlink" href="#dropout" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Dropout">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout" title="Permalink to this definition">#</a></dt>
 <dd><p>During training, randomly zeroes some of the elements of the input tensor with probability <code class="xref py py-attr docutils literal notranslate"><span class="pre">p</span></code>.</p>
 <p>The zeroed elements are chosen independently for each forward call and are sampled from a Bernoulli distribution.</p>
 <p>Each channel will be zeroed out independently on every forward call.</p>
@@ -4438,7 +4438,7 @@ <h1>Dropout<a class="headerlink" href="#dropout" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Dropout.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Dropout1d.html b/2.9/generated/torch.nn.Dropout1d.html
index 444188a671e..866a911de3d 100644
--- a/2.9/generated/torch.nn.Dropout1d.html
+++ b/2.9/generated/torch.nn.Dropout1d.html
@@ -4404,7 +4404,7 @@
 <h1>Dropout1d<a class="headerlink" href="#dropout1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Dropout1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Dropout1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Dropout1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels.</p>
 <p>A channel is a 1D feature map,
 e.g., the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
@@ -4444,7 +4444,7 @@ <h1>Dropout1d<a class="headerlink" href="#dropout1d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Dropout1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Dropout2d.html b/2.9/generated/torch.nn.Dropout2d.html
index 5eae7f14f2f..c89ed871f49 100644
--- a/2.9/generated/torch.nn.Dropout2d.html
+++ b/2.9/generated/torch.nn.Dropout2d.html
@@ -4404,7 +4404,7 @@
 <h1>Dropout2d<a class="headerlink" href="#dropout2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Dropout2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Dropout2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Dropout2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels.</p>
 <p>A channel is a 2D feature map,
 e.g., the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
@@ -4452,7 +4452,7 @@ <h1>Dropout2d<a class="headerlink" href="#dropout2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Dropout2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Dropout3d.html b/2.9/generated/torch.nn.Dropout3d.html
index a0d54b5784f..69ab45cba8e 100644
--- a/2.9/generated/torch.nn.Dropout3d.html
+++ b/2.9/generated/torch.nn.Dropout3d.html
@@ -4404,7 +4404,7 @@
 <h1>Dropout3d<a class="headerlink" href="#dropout3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Dropout3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Dropout3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Dropout3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels.</p>
 <p>A channel is a 3D feature map,
 e.g., the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
@@ -4444,7 +4444,7 @@ <h1>Dropout3d<a class="headerlink" href="#dropout3d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Dropout3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Dropout3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ELU.html b/2.9/generated/torch.nn.ELU.html
index bd4c76f1a20..cac18d3f7e6 100644
--- a/2.9/generated/torch.nn.ELU.html
+++ b/2.9/generated/torch.nn.ELU.html
@@ -4404,7 +4404,7 @@
 <h1>ELU<a class="headerlink" href="#elu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L573"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L573"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ELU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Exponential Linear Unit (ELU) function, element-wise.</p>
 <p>Method described in the paper: <a class="reference external" href="https://arxiv.org/abs/1511.07289">Fast and Accurate Deep Network Learning by Exponential Linear
 Units (ELUs)</a>.</p>
@@ -4439,7 +4439,7 @@ <h1>ELU<a class="headerlink" href="#elu" title="Permalink to this heading">#</a>
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ELU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L619"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ELU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L619"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ELU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4450,7 +4450,7 @@ <h1>ELU<a class="headerlink" href="#elu" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ELU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L613"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ELU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L613"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ELU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Embedding.html b/2.9/generated/torch.nn.Embedding.html
index f76645eb56b..7f310afe4f5 100644
--- a/2.9/generated/torch.nn.Embedding.html
+++ b/2.9/generated/torch.nn.Embedding.html
@@ -4404,7 +4404,7 @@
 <h1>Embedding<a class="headerlink" href="#embedding" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Embedding">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Embedding" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Embedding" title="Permalink to this definition">#</a></dt>
 <dd><p>A simple lookup table that stores embeddings of a fixed dictionary and size.</p>
 <p>This module is often used to store word embeddings and retrieve them using indices.
 The input to the module is a list of indices, and the output is the corresponding
@@ -4512,7 +4512,7 @@ <h1>Embedding<a class="headerlink" href="#embedding" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Embedding.from_pretrained">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_pretrained</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Embedding.from_pretrained" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_pretrained</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Embedding.from_pretrained" title="Permalink to this definition">#</a></dt>
 <dd><p>Create Embedding instance from given 2-dimensional FloatTensor.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.EmbeddingBag.html b/2.9/generated/torch.nn.EmbeddingBag.html
index 0e055863d31..aab2ea73144 100644
--- a/2.9/generated/torch.nn.EmbeddingBag.html
+++ b/2.9/generated/torch.nn.EmbeddingBag.html
@@ -4404,7 +4404,7 @@
 <h1>EmbeddingBag<a class="headerlink" href="#embeddingbag" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.EmbeddingBag">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">EmbeddingBag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.EmbeddingBag" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">EmbeddingBag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.EmbeddingBag" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute sums or means of ‘bags’ of embeddings, without instantiating the intermediate embeddings.</p>
 <p>For bags of constant length, no <code class="xref py py-attr docutils literal notranslate"><span class="pre">per_sample_weights</span></code>, no indices equal to <code class="xref py py-attr docutils literal notranslate"><span class="pre">padding_idx</span></code>,
 and with 2D inputs, this class</p>
@@ -4485,7 +4485,7 @@ <h1>EmbeddingBag<a class="headerlink" href="#embeddingbag" title="Permalink to t
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.EmbeddingBag.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offsets</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">per_sample_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.EmbeddingBag.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offsets</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">per_sample_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.EmbeddingBag.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Forward pass of EmbeddingBag.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4525,7 +4525,7 @@ <h1>EmbeddingBag<a class="headerlink" href="#embeddingbag" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.EmbeddingBag.from_pretrained">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_pretrained</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L492"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.EmbeddingBag.from_pretrained" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_pretrained</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L492"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.EmbeddingBag.from_pretrained" title="Permalink to this definition">#</a></dt>
 <dd><p>Create EmbeddingBag instance from given 2-dimensional FloatTensor.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.FeatureAlphaDropout.html b/2.9/generated/torch.nn.FeatureAlphaDropout.html
index c7db0894ea8..c018e47e016 100644
--- a/2.9/generated/torch.nn.FeatureAlphaDropout.html
+++ b/2.9/generated/torch.nn.FeatureAlphaDropout.html
@@ -4404,7 +4404,7 @@
 <h1>FeatureAlphaDropout<a class="headerlink" href="#featurealphadropout" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.FeatureAlphaDropout">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">FeatureAlphaDropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.FeatureAlphaDropout" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">FeatureAlphaDropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.FeatureAlphaDropout" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly masks out entire channels.</p>
 <p>A channel is a feature map,
 e.g. the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the batch input
@@ -4449,7 +4449,7 @@ <h1>FeatureAlphaDropout<a class="headerlink" href="#featurealphadropout" title="
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.FeatureAlphaDropout.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L319"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.FeatureAlphaDropout.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L319"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.FeatureAlphaDropout.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Fold.html b/2.9/generated/torch.nn.Fold.html
index 8260ffeea20..f6fbe138d07 100644
--- a/2.9/generated/torch.nn.Fold.html
+++ b/2.9/generated/torch.nn.Fold.html
@@ -4404,7 +4404,7 @@
 <h1>Fold<a class="headerlink" href="#fold" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Fold">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Fold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Fold" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Fold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Fold" title="Permalink to this definition">#</a></dt>
 <dd><p>Combines an array of sliding local blocks into a large containing tensor.</p>
 <p>Consider a batched <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> tensor containing sliding local blocks,
 e.g., patches of images, of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo>×</mo><mo>∏</mo><mo stretchy="false">(</mo><mtext>kernel_size</mtext><mo stretchy="false">)</mo><mo separator="true">,</mo><mi>L</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C \times  \prod(\text{kernel\_size}), L)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1.06em;vertical-align:-0.31em;"></span><span class="mop op-symbol small-op" style="position:relative;top:0em;">∏</span><span class="mopen">(</span><span class="mord text"><span class="mord">kernel_size</span></span><span class="mclose">)</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">L</span><span class="mclose">)</span></span></span></span></span>,
@@ -4514,7 +4514,7 @@ <h1>Fold<a class="headerlink" href="#fold" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Fold.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Fold.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Fold.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4525,7 +4525,7 @@ <h1>Fold<a class="headerlink" href="#fold" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Fold.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Fold.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Fold.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.FractionalMaxPool2d.html b/2.9/generated/torch.nn.FractionalMaxPool2d.html
index 2a0a9597883..40f77bb7ded 100644
--- a/2.9/generated/torch.nn.FractionalMaxPool2d.html
+++ b/2.9/generated/torch.nn.FractionalMaxPool2d.html
@@ -4404,7 +4404,7 @@
 <h1>FractionalMaxPool2d<a class="headerlink" href="#fractionalmaxpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.FractionalMaxPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">FractionalMaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L915"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.FractionalMaxPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">FractionalMaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L915"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.FractionalMaxPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D fractional max pooling over an input signal composed of several input planes.</p>
 <p>Fractional MaxPooling is described in detail in the paper <a class="reference external" href="https://arxiv.org/abs/1412.6071">Fractional MaxPooling</a> by Ben Graham</p>
 <p>The max-pooling operation is applied in <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi><mi>H</mi><mo>×</mo><mi>k</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">kH \times kW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span></span></span></span></span> regions by a stochastic
diff --git a/2.9/generated/torch.nn.FractionalMaxPool3d.html b/2.9/generated/torch.nn.FractionalMaxPool3d.html
index b4a1f1701fd..e4fffd7a602 100644
--- a/2.9/generated/torch.nn.FractionalMaxPool3d.html
+++ b/2.9/generated/torch.nn.FractionalMaxPool3d.html
@@ -4404,7 +4404,7 @@
 <h1>FractionalMaxPool3d<a class="headerlink" href="#fractionalmaxpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.FractionalMaxPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">FractionalMaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1004"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.FractionalMaxPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">FractionalMaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1004"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.FractionalMaxPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D fractional max pooling over an input signal composed of several input planes.</p>
 <p>Fractional MaxPooling is described in detail in the paper <a class="reference external" href="https://arxiv.org/abs/1412.6071">Fractional MaxPooling</a> by Ben Graham</p>
 <p>The max-pooling operation is applied in <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi><mi>T</mi><mo>×</mo><mi>k</mi><mi>H</mi><mo>×</mo><mi>k</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">kT \times kH \times kW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.13889em;">T</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span></span></span></span></span> regions by a stochastic
diff --git a/2.9/generated/torch.nn.GELU.html b/2.9/generated/torch.nn.GELU.html
index f30e6a7b6af..c6415a22ad6 100644
--- a/2.9/generated/torch.nn.GELU.html
+++ b/2.9/generated/torch.nn.GELU.html
@@ -4404,7 +4404,7 @@
 <h1>GELU<a class="headerlink" href="#gelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.GELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">approximate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'none'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L777"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">approximate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'none'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L777"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GELU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Gaussian Error Linear Units function.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>GELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>x</mi><mo>∗</mo><mi mathvariant="normal">Φ</mi><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{GELU}(x) = x * \Phi(x)
@@ -4446,7 +4446,7 @@ <h1>GELU<a class="headerlink" href="#gelu" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.GELU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L818"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GELU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L818"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GELU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4457,7 +4457,7 @@ <h1>GELU<a class="headerlink" href="#gelu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.GELU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L812"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GELU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L812"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GELU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.GLU.html b/2.9/generated/torch.nn.GLU.html
index b39a01e8a21..9c3f2c37a76 100644
--- a/2.9/generated/torch.nn.GLU.html
+++ b/2.9/generated/torch.nn.GLU.html
@@ -4404,7 +4404,7 @@
 <h1>GLU<a class="headerlink" href="#glu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.GLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L734"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L734"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the gated linear unit function.</p>
 <p><span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mrow><mi>G</mi><mi>L</mi><mi>U</mi></mrow><mo stretchy="false">(</mo><mi>a</mi><mo separator="true">,</mo><mi>b</mi><mo stretchy="false">)</mo><mo>=</mo><mi>a</mi><mo>⊗</mo><mi>σ</mi><mo stretchy="false">(</mo><mi>b</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">{GLU}(a, b)= a \otimes \sigma(b)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal">G</span><span class="mord mathnormal" style="margin-right:0.10903em;">LU</span></span><span class="mopen">(</span><span class="mord mathnormal">a</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">b</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.6667em;vertical-align:-0.0833em;"></span><span class="mord mathnormal">a</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">⊗</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">σ</span><span class="mopen">(</span><span class="mord mathnormal">b</span><span class="mclose">)</span></span></span></span></span> where <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>a</mi></mrow><annotation encoding="application/x-tex">a</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">a</span></span></span></span></span> is the first half
 of the input matrices and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>b</mi></mrow><annotation encoding="application/x-tex">b</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal">b</span></span></span></span></span> is the second half.</p>
@@ -4430,7 +4430,7 @@ <h1>GLU<a class="headerlink" href="#glu" title="Permalink to this heading">#</a>
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.GLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L770"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L770"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4441,7 +4441,7 @@ <h1>GLU<a class="headerlink" href="#glu" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.GLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L764"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L764"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.GRU.html b/2.9/generated/torch.nn.GRU.html
index a27b47b82e5..2d04e19240d 100644
--- a/2.9/generated/torch.nn.GRU.html
+++ b/2.9/generated/torch.nn.GRU.html
@@ -4404,7 +4404,7 @@
 <h1>GRU<a class="headerlink" href="#gru" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.GRU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GRU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L1165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GRU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GRU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L1165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GRU" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a multi-layer gated recurrent unit (GRU) RNN to an input sequence.
 For each element in the input sequence, each layer computes the following
 function:</p>
diff --git a/2.9/generated/torch.nn.GRUCell.html b/2.9/generated/torch.nn.GRUCell.html
index 65437de7bd9..8707782e4b3 100644
--- a/2.9/generated/torch.nn.GRUCell.html
+++ b/2.9/generated/torch.nn.GRUCell.html
@@ -4404,7 +4404,7 @@
 <h1>GRUCell<a class="headerlink" href="#grucell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.GRUCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GRUCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L1721"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GRUCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GRUCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L1721"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GRUCell" title="Permalink to this definition">#</a></dt>
 <dd><p>A gated recurrent unit (GRU) cell.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.16em" columnalign="left left" columnspacing="1em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>r</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>r</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>r</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>r</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>r</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>z</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>z</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>z</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>z</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>z</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>n</mi><mo>=</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>n</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>n</mi></mrow></msub><mo>+</mo><mi>r</mi><mo>⊙</mo><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>n</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>n</mi></mrow></msub><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><msup><mi>h</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo>=</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>z</mi><mo stretchy="false">)</mo><mo>⊙</mo><mi>n</mi><mo>+</mo><mi>z</mi><mo>⊙</mo><mi>h</mi></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{array}{ll}
diff --git a/2.9/generated/torch.nn.GaussianNLLLoss.html b/2.9/generated/torch.nn.GaussianNLLLoss.html
index 970fbede3b8..8b4d7712d02 100644
--- a/2.9/generated/torch.nn.GaussianNLLLoss.html
+++ b/2.9/generated/torch.nn.GaussianNLLLoss.html
@@ -4404,7 +4404,7 @@
 <h1>GaussianNLLLoss<a class="headerlink" href="#gaussiannllloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.GaussianNLLLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GaussianNLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L376"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GaussianNLLLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GaussianNLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L376"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GaussianNLLLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Gaussian negative log likelihood loss.</p>
 <p>The targets are treated as samples from Gaussian distributions with
 expectations and variances predicted by the neural network. For a
@@ -4480,7 +4480,7 @@ <h1>GaussianNLLLoss<a class="headerlink" href="#gaussiannllloss" title="Permalin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.GaussianNLLLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">var</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GaussianNLLLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">var</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GaussianNLLLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.GroupNorm.html b/2.9/generated/torch.nn.GroupNorm.html
index 08d37119b6e..cccb6069462 100644
--- a/2.9/generated/torch.nn.GroupNorm.html
+++ b/2.9/generated/torch.nn.GroupNorm.html
@@ -4404,7 +4404,7 @@
 <h1>GroupNorm<a class="headerlink" href="#groupnorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.GroupNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GroupNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_groups</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GroupNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">GroupNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_groups</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.GroupNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Group Normalization over a mini-batch of inputs.</p>
 <p>This layer implements the operation as described in
 the paper <a class="reference external" href="https://arxiv.org/abs/1803.08494">Group Normalization</a></p>
diff --git a/2.9/generated/torch.nn.Hardshrink.html b/2.9/generated/torch.nn.Hardshrink.html
index 31dcafedc48..1521ff4621c 100644
--- a/2.9/generated/torch.nn.Hardshrink.html
+++ b/2.9/generated/torch.nn.Hardshrink.html
@@ -4404,7 +4404,7 @@
 <h1>Hardshrink<a class="headerlink" href="#hardshrink" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Hardshrink">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Hardshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L825"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardshrink" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Hardshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L825"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardshrink" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Hard Shrinkage (Hardshrink) function element-wise.</p>
 <p>Hardshrink is defined as:</p>
 <div class="math">
@@ -4436,7 +4436,7 @@ <h1>Hardshrink<a class="headerlink" href="#hardshrink" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Hardshrink.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L867"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardshrink.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L867"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardshrink.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4447,7 +4447,7 @@ <h1>Hardshrink<a class="headerlink" href="#hardshrink" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Hardshrink.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L861"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardshrink.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L861"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardshrink.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Hardsigmoid.html b/2.9/generated/torch.nn.Hardsigmoid.html
index 904e7184816..f69d6571510 100644
--- a/2.9/generated/torch.nn.Hardsigmoid.html
+++ b/2.9/generated/torch.nn.Hardsigmoid.html
@@ -4404,7 +4404,7 @@
 <h1>Hardsigmoid<a class="headerlink" href="#hardsigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Hardsigmoid">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Hardsigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardsigmoid" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Hardsigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardsigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Hardsigmoid function element-wise.</p>
 <p>Hardsigmoid is defined as:</p>
 <div class="math">
@@ -4435,7 +4435,7 @@ <h1>Hardsigmoid<a class="headerlink" href="#hardsigmoid" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Hardsigmoid.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L398"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardsigmoid.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L398"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardsigmoid.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Hardswish.html b/2.9/generated/torch.nn.Hardswish.html
index 5a4cf31bf73..d07b5ae512c 100644
--- a/2.9/generated/torch.nn.Hardswish.html
+++ b/2.9/generated/torch.nn.Hardswish.html
@@ -4404,7 +4404,7 @@
 <h1>Hardswish<a class="headerlink" href="#hardswish" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Hardswish">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardswish" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardswish" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Hardswish function, element-wise.</p>
 <p>Method described in the paper: <a class="reference external" href="https://arxiv.org/abs/1905.02244">Searching for MobileNetV3</a>.</p>
 <p>Hardswish is defined as:</p>
@@ -4436,7 +4436,7 @@ <h1>Hardswish<a class="headerlink" href="#hardswish" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Hardswish.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardswish.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardswish.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Hardtanh.html b/2.9/generated/torch.nn.Hardtanh.html
index 668b18ab618..4b6bc0576af 100644
--- a/2.9/generated/torch.nn.Hardtanh.html
+++ b/2.9/generated/torch.nn.Hardtanh.html
@@ -4404,7 +4404,7 @@
 <h1>Hardtanh<a class="headerlink" href="#hardtanh" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Hardtanh">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Hardtanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">min_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardtanh" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Hardtanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">min_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardtanh" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the HardTanh function element-wise.</p>
 <p>HardTanh is defined as:</p>
 <div class="math">
@@ -4441,7 +4441,7 @@ <h1>Hardtanh<a class="headerlink" href="#hardtanh" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Hardtanh.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardtanh.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardtanh.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4452,7 +4452,7 @@ <h1>Hardtanh<a class="headerlink" href="#hardtanh" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Hardtanh.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L288"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardtanh.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L288"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Hardtanh.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.HingeEmbeddingLoss.html b/2.9/generated/torch.nn.HingeEmbeddingLoss.html
index 98e1e7be663..1fa5a4a209c 100644
--- a/2.9/generated/torch.nn.HingeEmbeddingLoss.html
+++ b/2.9/generated/torch.nn.HingeEmbeddingLoss.html
@@ -4404,7 +4404,7 @@
 <h1>HingeEmbeddingLoss<a class="headerlink" href="#hingeembeddingloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.HingeEmbeddingLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">HingeEmbeddingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L859"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.HingeEmbeddingLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">HingeEmbeddingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L859"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.HingeEmbeddingLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Measures the loss given an input tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and a labels tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span>
 (containing 1 or -1).
 This is usually used for measuring whether two inputs are similar or
@@ -4458,7 +4458,7 @@ <h1>HingeEmbeddingLoss<a class="headerlink" href="#hingeembeddingloss" title="Pe
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.HingeEmbeddingLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L922"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.HingeEmbeddingLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L922"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.HingeEmbeddingLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.HuberLoss.html b/2.9/generated/torch.nn.HuberLoss.html
index c9c229f31ed..3a908a5c1aa 100644
--- a/2.9/generated/torch.nn.HuberLoss.html
+++ b/2.9/generated/torch.nn.HuberLoss.html
@@ -4404,7 +4404,7 @@
 <h1>HuberLoss<a class="headerlink" href="#huberloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.HuberLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">HuberLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1080"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.HuberLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">HuberLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1080"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.HuberLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that uses a squared term if the absolute
 element-wise error falls below delta and a delta-scaled L1 term otherwise.
 This loss combines advantages of both <a class="reference internal" href="torch.nn.L1Loss.html#torch.nn.L1Loss" title="torch.nn.L1Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">L1Loss</span></code></a> and <a class="reference internal" href="torch.nn.MSELoss.html#torch.nn.MSELoss" title="torch.nn.MSELoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">MSELoss</span></code></a>; the
@@ -4460,7 +4460,7 @@ <h1>HuberLoss<a class="headerlink" href="#huberloss" title="Permalink to this he
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.HuberLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.HuberLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.HuberLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Identity.html b/2.9/generated/torch.nn.Identity.html
index 90d4ed1b6ec..63d7e837efd 100644
--- a/2.9/generated/torch.nn.Identity.html
+++ b/2.9/generated/torch.nn.Identity.html
@@ -4404,7 +4404,7 @@
 <h1>Identity<a class="headerlink" href="#identity" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Identity">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Identity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Identity" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Identity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Identity" title="Permalink to this definition">#</a></dt>
 <dd><p>A placeholder identity operator that is argument-insensitive.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4431,7 +4431,7 @@ <h1>Identity<a class="headerlink" href="#identity" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Identity.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Identity.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Identity.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.InstanceNorm1d.html b/2.9/generated/torch.nn.InstanceNorm1d.html
index 54f7cb07190..9fed35d3e55 100644
--- a/2.9/generated/torch.nn.InstanceNorm1d.html
+++ b/2.9/generated/torch.nn.InstanceNorm1d.html
@@ -4404,7 +4404,7 @@
 <h1>InstanceNorm1d<a class="headerlink" href="#instancenorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.InstanceNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.InstanceNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.InstanceNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Instance Normalization.</p>
 <p>This operation applies Instance Normalization
 over a 2D (unbatched) or 3D (batched) input as described in the paper
diff --git a/2.9/generated/torch.nn.InstanceNorm2d.html b/2.9/generated/torch.nn.InstanceNorm2d.html
index d8d8208ec42..7c56b5b5f28 100644
--- a/2.9/generated/torch.nn.InstanceNorm2d.html
+++ b/2.9/generated/torch.nn.InstanceNorm2d.html
@@ -4404,7 +4404,7 @@
 <h1>InstanceNorm2d<a class="headerlink" href="#instancenorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.InstanceNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.InstanceNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.InstanceNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Instance Normalization.</p>
 <p>This operation applies Instance Normalization
 over a 4D input (a mini-batch of 2D inputs
diff --git a/2.9/generated/torch.nn.InstanceNorm3d.html b/2.9/generated/torch.nn.InstanceNorm3d.html
index c688330cca7..e98853b1294 100644
--- a/2.9/generated/torch.nn.InstanceNorm3d.html
+++ b/2.9/generated/torch.nn.InstanceNorm3d.html
@@ -4404,7 +4404,7 @@
 <h1>InstanceNorm3d<a class="headerlink" href="#instancenorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.InstanceNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.InstanceNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.InstanceNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Instance Normalization.</p>
 <p>This operation applies Instance Normalization
 over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper
diff --git a/2.9/generated/torch.nn.KLDivLoss.html b/2.9/generated/torch.nn.KLDivLoss.html
index d90efeb8f55..a4684df8267 100644
--- a/2.9/generated/torch.nn.KLDivLoss.html
+++ b/2.9/generated/torch.nn.KLDivLoss.html
@@ -4404,7 +4404,7 @@
 <h1>KLDivLoss<a class="headerlink" href="#kldivloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.KLDivLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">KLDivLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L465"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.KLDivLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">KLDivLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L465"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.KLDivLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>The Kullback-Leibler divergence loss.</p>
 <p>For tensors of the same shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>y</mi><mtext>pred</mtext></msub><mo separator="true">,</mo><mtext> </mtext><msub><mi>y</mi><mtext>true</mtext></msub></mrow><annotation encoding="application/x-tex">y_{\text{pred}},\ y_{\text{true}}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7167em;vertical-align:-0.2861em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">pred</span></span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2861em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace"> </span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">true</span></span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>,
 where <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>y</mi><mtext>pred</mtext></msub></mrow><annotation encoding="application/x-tex">y_{\text{pred}}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7167em;vertical-align:-0.2861em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">pred</span></span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2861em;"><span></span></span></span></span></span></span></span></span></span></span> is the <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>y</mi><mtext>true</mtext></msub></mrow><annotation encoding="application/x-tex">y_{\text{true}}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">true</span></span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> is the
@@ -4487,7 +4487,7 @@ <h1>KLDivLoss<a class="headerlink" href="#kldivloss" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.KLDivLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.KLDivLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.KLDivLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.L1Loss.html b/2.9/generated/torch.nn.L1Loss.html
index 41a44714349..9a483467672 100644
--- a/2.9/generated/torch.nn.L1Loss.html
+++ b/2.9/generated/torch.nn.L1Loss.html
@@ -4404,7 +4404,7 @@
 <h1>L1Loss<a class="headerlink" href="#l1loss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.L1Loss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">L1Loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.L1Loss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">L1Loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.L1Loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the mean absolute error (MAE) between each element in
 the input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and target <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span>.</p>
 <p>The unreduced (i.e. with <code class="xref py py-attr docutils literal notranslate"><span class="pre">reduction</span></code> set to <code class="docutils literal notranslate"><span class="pre">'none'</span></code>) loss can be described as:</p>
@@ -4466,7 +4466,7 @@ <h1>L1Loss<a class="headerlink" href="#l1loss" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.L1Loss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.L1Loss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.L1Loss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.LPPool1d.html b/2.9/generated/torch.nn.LPPool1d.html
index 37e3f65de95..4e79ade8840 100644
--- a/2.9/generated/torch.nn.LPPool1d.html
+++ b/2.9/generated/torch.nn.LPPool1d.html
@@ -4404,7 +4404,7 @@
 <h1>LPPool1d<a class="headerlink" href="#lppool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LPPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LPPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LPPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D power-average pooling over an input signal composed of several input planes.</p>
 <p>On each window, the function computed is:</p>
 <div class="math">
@@ -4455,7 +4455,7 @@ <h1>LPPool1d<a class="headerlink" href="#lppool1d" title="Permalink to this head
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LPPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.LPPool2d.html b/2.9/generated/torch.nn.LPPool2d.html
index 0147081c2a3..c64a083219b 100644
--- a/2.9/generated/torch.nn.LPPool2d.html
+++ b/2.9/generated/torch.nn.LPPool2d.html
@@ -4404,7 +4404,7 @@
 <h1>LPPool2d<a class="headerlink" href="#lppool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LPPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LPPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LPPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D power-average pooling over an input signal composed of several input planes.</p>
 <p>On each window, the function computed is:</p>
 <div class="math">
@@ -4468,7 +4468,7 @@ <h1>LPPool2d<a class="headerlink" href="#lppool2d" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LPPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.LPPool3d.html b/2.9/generated/torch.nn.LPPool3d.html
index 2d2c21bd184..df933e9f5e9 100644
--- a/2.9/generated/torch.nn.LPPool3d.html
+++ b/2.9/generated/torch.nn.LPPool3d.html
@@ -4404,7 +4404,7 @@
 <h1>LPPool3d<a class="headerlink" href="#lppool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LPPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LPPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LPPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D power-average pooling over an input signal composed of several input planes.</p>
 <p>On each window, the function computed is:</p>
 <div class="math">
@@ -4472,7 +4472,7 @@ <h1>LPPool3d<a class="headerlink" href="#lppool3d" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LPPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1277"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1277"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LPPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.LSTM.html b/2.9/generated/torch.nn.LSTM.html
index 7146d195c8a..3a623f01684 100644
--- a/2.9/generated/torch.nn.LSTM.html
+++ b/2.9/generated/torch.nn.LSTM.html
@@ -4404,7 +4404,7 @@
 <h1>LSTM<a class="headerlink" href="#lstm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LSTM">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LSTM</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proj_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L800"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LSTM" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LSTM</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proj_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L800"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LSTM" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a multi-layer long short-term memory (LSTM) RNN to an input sequence.
 For each element in the input sequence, each layer computes the following
 function:</p>
diff --git a/2.9/generated/torch.nn.LSTMCell.html b/2.9/generated/torch.nn.LSTMCell.html
index 42d15872656..d74c1acc728 100644
--- a/2.9/generated/torch.nn.LSTMCell.html
+++ b/2.9/generated/torch.nn.LSTMCell.html
@@ -4404,7 +4404,7 @@
 <h1>LSTMCell<a class="headerlink" href="#lstmcell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LSTMCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LSTMCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L1611"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LSTMCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LSTMCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L1611"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LSTMCell" title="Permalink to this definition">#</a></dt>
 <dd><p>A long short-term memory (LSTM) cell.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.16em" columnalign="left left" columnspacing="1em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>i</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>i</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>i</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>i</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>i</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>f</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>f</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>f</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>f</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>f</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>g</mi><mo>=</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>g</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>g</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>g</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>g</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>o</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>o</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>o</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>o</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>o</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><msup><mi>c</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo>=</mo><mi>f</mi><mo>⊙</mo><mi>c</mi><mo>+</mo><mi>i</mi><mo>⊙</mo><mi>g</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><msup><mi>h</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo>=</mo><mi>o</mi><mo>⊙</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><msup><mi>c</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{array}{ll}
diff --git a/2.9/generated/torch.nn.LayerNorm.html b/2.9/generated/torch.nn.LayerNorm.html
index 2941787f5cb..02d4fe6fa65 100644
--- a/2.9/generated/torch.nn.LayerNorm.html
+++ b/2.9/generated/torch.nn.LayerNorm.html
@@ -4404,7 +4404,7 @@
 <h1>LayerNorm<a class="headerlink" href="#layernorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LayerNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LayerNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L106"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LayerNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LayerNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L106"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LayerNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Layer Normalization over a mini-batch of inputs.</p>
 <p>This layer implements the operation as described in
 the paper <a class="reference external" href="https://arxiv.org/abs/1607.06450">Layer Normalization</a></p>
diff --git a/2.9/generated/torch.nn.LazyBatchNorm1d.html b/2.9/generated/torch.nn.LazyBatchNorm1d.html
index dc3fbc8ec24..c381368f76e 100644
--- a/2.9/generated/torch.nn.LazyBatchNorm1d.html
+++ b/2.9/generated/torch.nn.LazyBatchNorm1d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyBatchNorm1d<a class="headerlink" href="#lazybatchnorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyBatchNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L346"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L346"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.BatchNorm1d.html#torch.nn.BatchNorm1d" title="torch.nn.BatchNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.BatchNorm1d</span></code></a> module with lazy initialization.</p>
 <p>Lazy initialization based on the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.BatchNorm1d.html#torch.nn.BatchNorm1d" title="torch.nn.BatchNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm1d</span></code></a> that is inferred
 from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4433,7 +4433,7 @@ <h1>LazyBatchNorm1d<a class="headerlink" href="#lazybatchnorm1d" title="Permalin
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyBatchNorm1d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm1d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm1d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm1d.html#torch.nn.modules.batchnorm.BatchNorm1d" title="torch.nn.modules.batchnorm.BatchNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm1d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyBatchNorm2d.html b/2.9/generated/torch.nn.LazyBatchNorm2d.html
index c8a54963d7b..dda5fb1ec92 100644
--- a/2.9/generated/torch.nn.LazyBatchNorm2d.html
+++ b/2.9/generated/torch.nn.LazyBatchNorm2d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyBatchNorm2d<a class="headerlink" href="#lazybatchnorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyBatchNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L457"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L457"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.BatchNorm2d.html#torch.nn.BatchNorm2d" title="torch.nn.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.BatchNorm2d</span></code></a> module with lazy initialization.</p>
 <p>Lazy initialization is done for the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.BatchNorm2d.html#torch.nn.BatchNorm2d" title="torch.nn.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm2d</span></code></a> that is inferred
 from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4433,7 +4433,7 @@ <h1>LazyBatchNorm2d<a class="headerlink" href="#lazybatchnorm2d" title="Permalin
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyBatchNorm2d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm2d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm2d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm2d.html#torch.nn.modules.batchnorm.BatchNorm2d" title="torch.nn.modules.batchnorm.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm2d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyBatchNorm3d.html b/2.9/generated/torch.nn.LazyBatchNorm3d.html
index 57194836fa5..ba4ab54bc1e 100644
--- a/2.9/generated/torch.nn.LazyBatchNorm3d.html
+++ b/2.9/generated/torch.nn.LazyBatchNorm3d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyBatchNorm3d<a class="headerlink" href="#lazybatchnorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyBatchNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L568"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L568"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.BatchNorm3d.html#torch.nn.BatchNorm3d" title="torch.nn.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.BatchNorm3d</span></code></a> module with lazy initialization.</p>
 <p>Lazy initialization is done for the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.BatchNorm3d.html#torch.nn.BatchNorm3d" title="torch.nn.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm3d</span></code></a> that is inferred
 from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4433,7 +4433,7 @@ <h1>LazyBatchNorm3d<a class="headerlink" href="#lazybatchnorm3d" title="Permalin
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyBatchNorm3d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L491"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm3d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L491"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyBatchNorm3d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm3d.html#torch.nn.modules.batchnorm.BatchNorm3d" title="torch.nn.modules.batchnorm.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm3d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyConv1d.html b/2.9/generated/torch.nn.LazyConv1d.html
index c97bd993bed..e6f0373316e 100644
--- a/2.9/generated/torch.nn.LazyConv1d.html
+++ b/2.9/generated/torch.nn.LazyConv1d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyConv1d<a class="headerlink" href="#lazyconv1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyConv1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.Conv1d.html#torch.nn.Conv1d" title="torch.nn.Conv1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Conv1d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.Conv1d.html#torch.nn.Conv1d" title="torch.nn.Conv1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv1d</span></code></a> is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite> and <cite>bias</cite>.</p>
@@ -4435,7 +4435,7 @@ <h1>LazyConv1d<a class="headerlink" href="#lazyconv1d" title="Permalink to this
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyConv1d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv1d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv1d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.Conv1d.html#torch.nn.modules.conv.Conv1d" title="torch.nn.modules.conv.Conv1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv1d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyConv2d.html b/2.9/generated/torch.nn.LazyConv2d.html
index 24b1d4437ec..1c02669b1ff 100644
--- a/2.9/generated/torch.nn.LazyConv2d.html
+++ b/2.9/generated/torch.nn.LazyConv2d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyConv2d<a class="headerlink" href="#lazyconv2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyConv2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1521"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1521"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.Conv2d.html#torch.nn.Conv2d" title="torch.nn.Conv2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Conv2d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.Conv2d.html#torch.nn.Conv2d" title="torch.nn.Conv2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv2d</span></code></a> that is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite> and <cite>bias</cite>.</p>
@@ -4435,7 +4435,7 @@ <h1>LazyConv2d<a class="headerlink" href="#lazyconv2d" title="Permalink to this
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyConv2d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv2d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv2d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.Conv2d.html#torch.nn.modules.conv.Conv2d" title="torch.nn.modules.conv.Conv2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv2d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyConv3d.html b/2.9/generated/torch.nn.LazyConv3d.html
index 9661bdc848a..ed565e4f582 100644
--- a/2.9/generated/torch.nn.LazyConv3d.html
+++ b/2.9/generated/torch.nn.LazyConv3d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyConv3d<a class="headerlink" href="#lazyconv3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyConv3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1590"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1590"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.Conv3d.html#torch.nn.Conv3d" title="torch.nn.Conv3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Conv3d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.Conv3d.html#torch.nn.Conv3d" title="torch.nn.Conv3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv3d</span></code></a> that is inferred from
 the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4436,7 +4436,7 @@ <h1>LazyConv3d<a class="headerlink" href="#lazyconv3d" title="Permalink to this
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyConv3d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv3d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConv3d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.Conv3d.html#torch.nn.modules.conv.Conv3d" title="torch.nn.modules.conv.Conv3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv3d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyConvTranspose1d.html b/2.9/generated/torch.nn.LazyConvTranspose1d.html
index ec37abec6c6..b7988f57311 100644
--- a/2.9/generated/torch.nn.LazyConvTranspose1d.html
+++ b/2.9/generated/torch.nn.LazyConvTranspose1d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyConvTranspose1d<a class="headerlink" href="#lazyconvtranspose1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyConvTranspose1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.ConvTranspose1d.html#torch.nn.ConvTranspose1d" title="torch.nn.ConvTranspose1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.ConvTranspose1d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.ConvTranspose1d.html#torch.nn.ConvTranspose1d" title="torch.nn.ConvTranspose1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose1d</span></code></a> that is inferred from
 the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4433,7 +4433,7 @@ <h1>LazyConvTranspose1d<a class="headerlink" href="#lazyconvtranspose1d" title="
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyConvTranspose1d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose1d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose1d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose1d.html#torch.nn.modules.conv.ConvTranspose1d" title="torch.nn.modules.conv.ConvTranspose1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose1d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyConvTranspose2d.html b/2.9/generated/torch.nn.LazyConvTranspose2d.html
index fb4c49e5811..bcc774c1f64 100644
--- a/2.9/generated/torch.nn.LazyConvTranspose2d.html
+++ b/2.9/generated/torch.nn.LazyConvTranspose2d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyConvTranspose2d<a class="headerlink" href="#lazyconvtranspose2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyConvTranspose2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1729"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1729"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.ConvTranspose2d.html#torch.nn.ConvTranspose2d" title="torch.nn.ConvTranspose2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.ConvTranspose2d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.ConvTranspose2d.html#torch.nn.ConvTranspose2d" title="torch.nn.ConvTranspose2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose2d</span></code></a> is inferred from
 the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4433,7 +4433,7 @@ <h1>LazyConvTranspose2d<a class="headerlink" href="#lazyconvtranspose2d" title="
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyConvTranspose2d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L976"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose2d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L976"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose2d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose2d.html#torch.nn.modules.conv.ConvTranspose2d" title="torch.nn.modules.conv.ConvTranspose2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose2d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyConvTranspose3d.html b/2.9/generated/torch.nn.LazyConvTranspose3d.html
index a3c2df525ea..28d75b735dd 100644
--- a/2.9/generated/torch.nn.LazyConvTranspose3d.html
+++ b/2.9/generated/torch.nn.LazyConvTranspose3d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyConvTranspose3d<a class="headerlink" href="#lazyconvtranspose3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyConvTranspose3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1798"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1798"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.ConvTranspose3d.html#torch.nn.ConvTranspose3d" title="torch.nn.ConvTranspose3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.ConvTranspose3d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.ConvTranspose3d.html#torch.nn.ConvTranspose3d" title="torch.nn.ConvTranspose3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose3d</span></code></a> is inferred from
 the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4433,7 +4433,7 @@ <h1>LazyConvTranspose3d<a class="headerlink" href="#lazyconvtranspose3d" title="
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyConvTranspose3d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose3d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyConvTranspose3d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose3d.html#torch.nn.modules.conv.ConvTranspose3d" title="torch.nn.modules.conv.ConvTranspose3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose3d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyInstanceNorm1d.html b/2.9/generated/torch.nn.LazyInstanceNorm1d.html
index 18a2af1a929..baf51cd92ae 100644
--- a/2.9/generated/torch.nn.LazyInstanceNorm1d.html
+++ b/2.9/generated/torch.nn.LazyInstanceNorm1d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyInstanceNorm1d<a class="headerlink" href="#lazyinstancenorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyInstanceNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.InstanceNorm1d.html#torch.nn.InstanceNorm1d" title="torch.nn.InstanceNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.InstanceNorm1d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.InstanceNorm1d.html#torch.nn.InstanceNorm1d" title="torch.nn.InstanceNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm1d</span></code></a> is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite>, <cite>bias</cite>, <cite>running_mean</cite> and <cite>running_var</cite>.</p>
@@ -4436,7 +4436,7 @@ <h1>LazyInstanceNorm1d<a class="headerlink" href="#lazyinstancenorm1d" title="Pe
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyInstanceNorm1d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm1d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm1d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm1d.html#torch.nn.modules.instancenorm.InstanceNorm1d" title="torch.nn.modules.instancenorm.InstanceNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm1d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyInstanceNorm2d.html b/2.9/generated/torch.nn.LazyInstanceNorm2d.html
index 0df58756008..2b1280e71b1 100644
--- a/2.9/generated/torch.nn.LazyInstanceNorm2d.html
+++ b/2.9/generated/torch.nn.LazyInstanceNorm2d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyInstanceNorm2d<a class="headerlink" href="#lazyinstancenorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyInstanceNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.InstanceNorm2d.html#torch.nn.InstanceNorm2d" title="torch.nn.InstanceNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.InstanceNorm2d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.InstanceNorm2d.html#torch.nn.InstanceNorm2d" title="torch.nn.InstanceNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm2d</span></code></a> is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite>, <cite>bias</cite>,
@@ -4437,7 +4437,7 @@ <h1>LazyInstanceNorm2d<a class="headerlink" href="#lazyinstancenorm2d" title="Pe
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyInstanceNorm2d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm2d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm2d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm2d.html#torch.nn.modules.instancenorm.InstanceNorm2d" title="torch.nn.modules.instancenorm.InstanceNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm2d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyInstanceNorm3d.html b/2.9/generated/torch.nn.LazyInstanceNorm3d.html
index 9213c093615..1b8078c05b5 100644
--- a/2.9/generated/torch.nn.LazyInstanceNorm3d.html
+++ b/2.9/generated/torch.nn.LazyInstanceNorm3d.html
@@ -4404,7 +4404,7 @@
 <h1>LazyInstanceNorm3d<a class="headerlink" href="#lazyinstancenorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyInstanceNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.InstanceNorm3d.html#torch.nn.InstanceNorm3d" title="torch.nn.InstanceNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.InstanceNorm3d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.InstanceNorm3d.html#torch.nn.InstanceNorm3d" title="torch.nn.InstanceNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm3d</span></code></a> is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite>, <cite>bias</cite>,
@@ -4437,7 +4437,7 @@ <h1>LazyInstanceNorm3d<a class="headerlink" href="#lazyinstancenorm3d" title="Pe
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyInstanceNorm3d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm3d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyInstanceNorm3d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm3d.html#torch.nn.modules.instancenorm.InstanceNorm3d" title="torch.nn.modules.instancenorm.InstanceNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm3d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.LazyLinear.html b/2.9/generated/torch.nn.LazyLinear.html
index 0ac16b6977a..cddfba5fff0 100644
--- a/2.9/generated/torch.nn.LazyLinear.html
+++ b/2.9/generated/torch.nn.LazyLinear.html
@@ -4404,7 +4404,7 @@
 <h1>LazyLinear<a class="headerlink" href="#lazylinear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LazyLinear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyLinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyLinear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LazyLinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyLinear" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.Linear.html#torch.nn.Linear" title="torch.nn.Linear"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Linear</span></code></a> module where <cite>in_features</cite> is inferred.</p>
 <p>In this module, the <cite>weight</cite> and <cite>bias</cite> are of <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.UninitializedParameter</span></code>
 class. They will be initialized after the first call to <code class="docutils literal notranslate"><span class="pre">forward</span></code> is done and the
@@ -4479,13 +4479,13 @@ <h1>LazyLinear<a class="headerlink" href="#lazylinear" title="Permalink to this
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.LazyLinear.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyLinear.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyLinear.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.linear.Linear.html#torch.nn.modules.linear.Linear" title="torch.nn.modules.linear.Linear"><code class="xref py py-class docutils literal notranslate"><span class="pre">Linear</span></code></a></p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LazyLinear.initialize_parameters">
-<span class="sig-name descname"><span class="pre">initialize_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyLinear.initialize_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">initialize_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyLinear.initialize_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Infers <code class="docutils literal notranslate"><span class="pre">in_features</span></code> based on <code class="docutils literal notranslate"><span class="pre">input</span></code> and initializes parameters.</p>
 <dl class="field-list simple">
 </dl>
@@ -4493,7 +4493,7 @@ <h1>LazyLinear<a class="headerlink" href="#lazylinear" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LazyLinear.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyLinear.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LazyLinear.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.LeakyReLU.html b/2.9/generated/torch.nn.LeakyReLU.html
index 0783dc473bf..db1c0ddd613 100644
--- a/2.9/generated/torch.nn.LeakyReLU.html
+++ b/2.9/generated/torch.nn.LeakyReLU.html
@@ -4404,7 +4404,7 @@
 <h1>LeakyReLU<a class="headerlink" href="#leakyrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LeakyReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LeakyReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L874"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LeakyReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LeakyReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L874"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LeakyReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the LeakyReLU function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>LeakyReLU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mtext>negative_slope</mtext><mo>∗</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{LeakyReLU}(x) = \max(0, x) + \text{negative\_slope} * \min(0, x)
@@ -4443,7 +4443,7 @@ <h1>LeakyReLU<a class="headerlink" href="#leakyrelu" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LeakyReLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L924"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LeakyReLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L924"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LeakyReLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4454,7 +4454,7 @@ <h1>LeakyReLU<a class="headerlink" href="#leakyrelu" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LeakyReLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L918"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LeakyReLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L918"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LeakyReLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Linear.html b/2.9/generated/torch.nn.Linear.html
index b04be0ac2a1..83c5bfb0705 100644
--- a/2.9/generated/torch.nn.Linear.html
+++ b/2.9/generated/torch.nn.Linear.html
@@ -4404,7 +4404,7 @@
 <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Linear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Linear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Linear" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies an affine linear transformation to the incoming data: <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mi>x</mi><msup><mi>A</mi><mi>T</mi></msup><mo>+</mo><mi>b</mi></mrow><annotation encoding="application/x-tex">y = xA^T + b</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.9247em;vertical-align:-0.0833em;"></span><span class="mord mathnormal">x</span><span class="mord"><span class="mord mathnormal">A</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8413em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight" style="margin-right:0.13889em;">T</span></span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal">b</span></span></span></span></span>.</p>
 <p>This module supports <a class="reference internal" href="../notes/cuda.html#tf32-on-ampere"><span class="std std-ref">TensorFloat32</span></a>.</p>
 <p>On certain ROCm devices, when using float16 inputs this module will use <a class="reference internal" href="../notes/numerical_accuracy.html#fp16-on-mi200"><span class="std std-ref">different precision</span></a> for backward.</p>
@@ -4495,7 +4495,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Linear.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Linear.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Linear.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4506,7 +4506,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Linear.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Linear.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Linear.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4517,7 +4517,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Linear.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Linear.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Linear.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.LocalResponseNorm.html b/2.9/generated/torch.nn.LocalResponseNorm.html
index 2eb1304d2bf..d4a58e3ab9e 100644
--- a/2.9/generated/torch.nn.LocalResponseNorm.html
+++ b/2.9/generated/torch.nn.LocalResponseNorm.html
@@ -4404,7 +4404,7 @@
 <h1>LocalResponseNorm<a class="headerlink" href="#localresponsenorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LocalResponseNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LocalResponseNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LocalResponseNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LocalResponseNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LocalResponseNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies local response normalization over an input signal.</p>
 <p>The input signal is composed of several input planes, where channels occupy the second dimension.
 Applies normalization across channels.</p>
@@ -4454,13 +4454,13 @@ <h1>LocalResponseNorm<a class="headerlink" href="#localresponsenorm" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LocalResponseNorm.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LocalResponseNorm.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LocalResponseNorm.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LocalResponseNorm.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LocalResponseNorm.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LocalResponseNorm.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.LogSigmoid.html b/2.9/generated/torch.nn.LogSigmoid.html
index 26098ad317e..1399a67a7a6 100644
--- a/2.9/generated/torch.nn.LogSigmoid.html
+++ b/2.9/generated/torch.nn.LogSigmoid.html
@@ -4404,7 +4404,7 @@
 <h1>LogSigmoid<a class="headerlink" href="#logsigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LogSigmoid">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LogSigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L932"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSigmoid" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LogSigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L932"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Logsigmoid function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>LogSigmoid</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>log</mi><mo>⁡</mo><mrow><mo fence="true">(</mo><mfrac><mn>1</mn><mrow><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow></mfrac><mo fence="true">)</mo></mrow></mrow><annotation encoding="application/x-tex">\text{LogSigmoid}(x) = \log\left(\frac{ 1 }{ 1 + \exp(-x)}\right)
@@ -4427,7 +4427,7 @@ <h1>LogSigmoid<a class="headerlink" href="#logsigmoid" title="Permalink to this
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LogSigmoid.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSigmoid.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSigmoid.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.LogSoftmax.html b/2.9/generated/torch.nn.LogSoftmax.html
index 9cee210fa5d..85cfb3c25bf 100644
--- a/2.9/generated/torch.nn.LogSoftmax.html
+++ b/2.9/generated/torch.nn.LogSoftmax.html
@@ -4404,7 +4404,7 @@
 <h1>LogSoftmax<a class="headerlink" href="#logsoftmax" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.LogSoftmax">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LogSoftmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSoftmax" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">LogSoftmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSoftmax" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>log</mi><mo>⁡</mo><mo stretchy="false">(</mo><mtext>Softmax</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\log(\text{Softmax}(x))</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">lo<span style="margin-right:0.01389em;">g</span></span><span class="mopen">(</span><span class="mord text"><span class="mord">Softmax</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">))</span></span></span></span></span> function to an n-dimensional input Tensor.</p>
 <p>The LogSoftmax formulation can be simplified as:</p>
 <div class="math">
@@ -4438,7 +4438,7 @@ <h1>LogSoftmax<a class="headerlink" href="#logsoftmax" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LogSoftmax.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1898"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSoftmax.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1898"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSoftmax.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4449,7 +4449,7 @@ <h1>LogSoftmax<a class="headerlink" href="#logsoftmax" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.LogSoftmax.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1892"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSoftmax.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1892"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.LogSoftmax.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.MSELoss.html b/2.9/generated/torch.nn.MSELoss.html
index 239c72a8bd4..46fc7cfb4cd 100644
--- a/2.9/generated/torch.nn.MSELoss.html
+++ b/2.9/generated/torch.nn.MSELoss.html
@@ -4404,7 +4404,7 @@
 <h1>MSELoss<a class="headerlink" href="#mseloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MSELoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MSELoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L568"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MSELoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MSELoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L568"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MSELoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the mean squared error (squared L2 norm) between
 each element in the input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and target <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span>.</p>
 <p>The unreduced (i.e. with <code class="xref py py-attr docutils literal notranslate"><span class="pre">reduction</span></code> set to <code class="docutils literal notranslate"><span class="pre">'none'</span></code>) loss can be described as:</p>
@@ -4463,7 +4463,7 @@ <h1>MSELoss<a class="headerlink" href="#mseloss" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MSELoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L630"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MSELoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L630"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MSELoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.MarginRankingLoss.html b/2.9/generated/torch.nn.MarginRankingLoss.html
index e835b9c8922..07d5e92e43b 100644
--- a/2.9/generated/torch.nn.MarginRankingLoss.html
+++ b/2.9/generated/torch.nn.MarginRankingLoss.html
@@ -4404,7 +4404,7 @@
 <h1>MarginRankingLoss<a class="headerlink" href="#marginrankingloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MarginRankingLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MarginRankingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1524"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MarginRankingLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MarginRankingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1524"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MarginRankingLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the loss given
 inputs <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>1</mn></mrow><annotation encoding="application/x-tex">x1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">1</span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>2</mn></mrow><annotation encoding="application/x-tex">x2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">2</span></span></span></span></span>, two 1D mini-batch or 0D <cite>Tensors</cite>,
 and a label 1D mini-batch or 0D <cite>Tensor</cite> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> (containing 1 or -1).</p>
@@ -4456,7 +4456,7 @@ <h1>MarginRankingLoss<a class="headerlink" href="#marginrankingloss" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MarginRankingLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1584"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MarginRankingLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1584"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MarginRankingLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.MaxPool1d.html b/2.9/generated/torch.nn.MaxPool1d.html
index b9a5d4473f5..53fc9e4616f 100644
--- a/2.9/generated/torch.nn.MaxPool1d.html
+++ b/2.9/generated/torch.nn.MaxPool1d.html
@@ -4404,7 +4404,7 @@
 <h1>MaxPool1d<a class="headerlink" href="#maxpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MaxPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L81"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L81"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D max pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>L</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, L)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">L</span><span class="mclose">)</span></span></span></span></span>
 and output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>L</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, L_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> can be precisely described as:</p>
@@ -4463,7 +4463,7 @@ <h1>MaxPool1d<a class="headerlink" href="#maxpool1d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MaxPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.MaxPool2d.html b/2.9/generated/torch.nn.MaxPool2d.html
index c9a4aebd660..3062f5b4f78 100644
--- a/2.9/generated/torch.nn.MaxPool2d.html
+++ b/2.9/generated/torch.nn.MaxPool2d.html
@@ -4404,7 +4404,7 @@
 <h1>MaxPool2d<a class="headerlink" href="#maxpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MaxPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D max pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, H_{out}, W_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>k</mi><mi>H</mi><mo separator="true">,</mo><mi>k</mi><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(kH, kW)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span><span class="mclose">)</span></span></span></span></span>
@@ -4472,7 +4472,7 @@ <h1>MaxPool2d<a class="headerlink" href="#maxpool2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MaxPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.MaxPool3d.html b/2.9/generated/torch.nn.MaxPool3d.html
index a0f96b01c3e..a49bdc55236 100644
--- a/2.9/generated/torch.nn.MaxPool3d.html
+++ b/2.9/generated/torch.nn.MaxPool3d.html
@@ -4404,7 +4404,7 @@
 <h1>MaxPool3d<a class="headerlink" href="#maxpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MaxPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D max pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>D</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, D, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>D</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, D_{out}, H_{out}, W_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>k</mi><mi>D</mi><mo separator="true">,</mo><mi>k</mi><mi>H</mi><mo separator="true">,</mo><mi>k</mi><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(kD, kH, kW)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span><span class="mclose">)</span></span></span></span></span>
@@ -4476,7 +4476,7 @@ <h1>MaxPool3d<a class="headerlink" href="#maxpool3d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MaxPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L308"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L308"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.MaxUnpool1d.html b/2.9/generated/torch.nn.MaxUnpool1d.html
index 074d92c7abc..2488241c9e2 100644
--- a/2.9/generated/torch.nn.MaxUnpool1d.html
+++ b/2.9/generated/torch.nn.MaxUnpool1d.html
@@ -4404,7 +4404,7 @@
 <h1>MaxUnpool1d<a class="headerlink" href="#maxunpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MaxUnpool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a partial inverse of <a class="reference internal" href="torch.nn.MaxPool1d.html#torch.nn.MaxPool1d" title="torch.nn.MaxPool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool1d</span></code></a>.</p>
 <p><a class="reference internal" href="torch.nn.MaxPool1d.html#torch.nn.MaxPool1d" title="torch.nn.MaxPool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool1d</span></code></a> is not fully invertible, since the non-maximal values are lost.</p>
 <p><a class="reference internal" href="#torch.nn.MaxUnpool1d" title="torch.nn.MaxUnpool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool1d</span></code></a> takes in as input the output of <a class="reference internal" href="torch.nn.MaxPool1d.html#torch.nn.MaxPool1d" title="torch.nn.MaxPool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool1d</span></code></a>
@@ -4471,7 +4471,7 @@ <h1>MaxUnpool1d<a class="headerlink" href="#maxunpool1d" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MaxUnpool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L400"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L400"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.MaxUnpool2d.html b/2.9/generated/torch.nn.MaxUnpool2d.html
index 512af3f3552..20b29653505 100644
--- a/2.9/generated/torch.nn.MaxUnpool2d.html
+++ b/2.9/generated/torch.nn.MaxUnpool2d.html
@@ -4404,7 +4404,7 @@
 <h1>MaxUnpool2d<a class="headerlink" href="#maxunpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MaxUnpool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a partial inverse of <a class="reference internal" href="torch.nn.MaxPool2d.html#torch.nn.MaxPool2d" title="torch.nn.MaxPool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool2d</span></code></a>.</p>
 <p><a class="reference internal" href="torch.nn.MaxPool2d.html#torch.nn.MaxPool2d" title="torch.nn.MaxPool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool2d</span></code></a> is not fully invertible, since the non-maximal values are lost.</p>
 <p><a class="reference internal" href="#torch.nn.MaxUnpool2d" title="torch.nn.MaxUnpool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool2d</span></code></a> takes in as input the output of <a class="reference internal" href="torch.nn.MaxPool2d.html#torch.nn.MaxPool2d" title="torch.nn.MaxPool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool2d</span></code></a>
@@ -4483,7 +4483,7 @@ <h1>MaxUnpool2d<a class="headerlink" href="#maxunpool2d" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MaxUnpool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L496"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L496"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.MaxUnpool3d.html b/2.9/generated/torch.nn.MaxUnpool3d.html
index c7687ceb102..40b42ece6ef 100644
--- a/2.9/generated/torch.nn.MaxUnpool3d.html
+++ b/2.9/generated/torch.nn.MaxUnpool3d.html
@@ -4404,7 +4404,7 @@
 <h1>MaxUnpool3d<a class="headerlink" href="#maxunpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MaxUnpool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L505"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L505"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a partial inverse of <a class="reference internal" href="torch.nn.MaxPool3d.html#torch.nn.MaxPool3d" title="torch.nn.MaxPool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool3d</span></code></a>.</p>
 <p><a class="reference internal" href="torch.nn.MaxPool3d.html#torch.nn.MaxPool3d" title="torch.nn.MaxPool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool3d</span></code></a> is not fully invertible, since the non-maximal values are lost.
 <a class="reference internal" href="#torch.nn.MaxUnpool3d" title="torch.nn.MaxUnpool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool3d</span></code></a> takes in as input the output of <a class="reference internal" href="torch.nn.MaxPool3d.html#torch.nn.MaxPool3d" title="torch.nn.MaxPool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool3d</span></code></a>
@@ -4469,7 +4469,7 @@ <h1>MaxUnpool3d<a class="headerlink" href="#maxunpool3d" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MaxUnpool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MaxUnpool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Mish.html b/2.9/generated/torch.nn.Mish.html
index dba115638aa..667989db887 100644
--- a/2.9/generated/torch.nn.Mish.html
+++ b/2.9/generated/torch.nn.Mish.html
@@ -4404,7 +4404,7 @@
 <h1>Mish<a class="headerlink" href="#mish" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Mish">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Mish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L483"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Mish" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Mish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L483"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Mish" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Mish function, element-wise.</p>
 <p>Mish: A Self Regularized Non-Monotonic Neural Activation Function.</p>
 <div class="math">
@@ -4432,7 +4432,7 @@ <h1>Mish<a class="headerlink" href="#mish" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Mish.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Mish.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Mish.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4443,7 +4443,7 @@ <h1>Mish<a class="headerlink" href="#mish" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Mish.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L514"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Mish.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L514"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Mish.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Module.html b/2.9/generated/torch.nn.Module.html
index fc286529b8e..c406003fe75 100644
--- a/2.9/generated/torch.nn.Module.html
+++ b/2.9/generated/torch.nn.Module.html
@@ -4404,7 +4404,7 @@
 <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Module">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L404"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L404"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class for all neural network modules.</p>
 <p>Your models should also subclass this class.</p>
 <p>Modules can also contain other Modules, allowing them to be nested in
@@ -4439,7 +4439,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.add_module">
-<span class="sig-name descname"><span class="pre">add_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L639"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.add_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L639"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.add_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a child module to the current module.</p>
 <p>The module can be accessed as an attribute using the given name.</p>
 <dl class="field-list simple">
@@ -4455,7 +4455,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.apply">
-<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.apply" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every submodule (as returned by <code class="docutils literal notranslate"><span class="pre">.children()</span></code>) as well as self.</p>
 <p>Typical use includes initializing the parameters of a model
 (see also <a class="reference internal" href="../nn.init.html#nn-init-doc"><span class="std std-ref">torch.nn.init</span></a>).</p>
@@ -4497,7 +4497,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.bfloat16">
-<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.bfloat16" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.bfloat16" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">bfloat16</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4515,7 +4515,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.buffers">
-<span class="sig-name descname"><span class="pre">buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2713"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2713"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module buffers.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4541,7 +4541,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.children">
-<span class="sig-name descname"><span class="pre">children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2767"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.children" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2767"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.children" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over immediate children modules.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -4555,7 +4555,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.compile">
-<span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L3030"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.compile" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L3030"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.compile" title="Permalink to this definition">#</a></dt>
 <dd><p>Compile this Module’s forward using <a class="reference internal" href="torch.compile.html#torch.compile" title="torch.compile"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.compile()</span></code></a>.</p>
 <p>This Module’s <cite>__call__</cite> method is compiled and all arguments are passed as-is
 to <a class="reference internal" href="torch.compile.html#torch.compile" title="torch.compile"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.compile()</span></code></a>.</p>
@@ -4564,7 +4564,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.cpu">
-<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.cpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.cpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the CPU.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4582,7 +4582,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.cuda">
-<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.cuda" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.cuda" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the GPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -4607,7 +4607,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.double">
-<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.double" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.double" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">double</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4625,7 +4625,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.eval">
-<span class="sig-name descname"><span class="pre">eval</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2894"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.eval" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">eval</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2894"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.eval" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module in evaluation mode.</p>
 <p>This has an effect only on certain modules. See the documentation of
 particular modules for details of their behaviors in training/evaluation
@@ -4646,7 +4646,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2970"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2970"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <p>To print customized extra information, you should re-implement
 this method in your own modules. Both single-line and multi-line
@@ -4660,7 +4660,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.float">
-<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.float" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.float" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">float</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4678,7 +4678,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L388"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L388"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Define the computation performed at every call.</p>
 <p>Should be overridden by all subclasses.</p>
 <div class="admonition note">
@@ -4694,7 +4694,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.get_buffer">
-<span class="sig-name descname"><span class="pre">get_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.get_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.get_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the buffer given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>See the docstring for <code class="docutils literal notranslate"><span class="pre">get_submodule</span></code> for a more detailed
 explanation of this method’s functionality as well as how to
@@ -4721,7 +4721,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.get_extra_state">
-<span class="sig-name descname"><span class="pre">get_extra_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L889"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.get_extra_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_extra_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L889"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.get_extra_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Return any extra state to include in the module’s state_dict.</p>
 <p>Implement this and a corresponding <a class="reference internal" href="#torch.nn.Module.set_extra_state" title="torch.nn.Module.set_extra_state"><code class="xref py py-func docutils literal notranslate"><span class="pre">set_extra_state()</span></code></a> for your module
 if you need to store extra state. This function is called when building the
@@ -4742,7 +4742,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.get_parameter">
-<span class="sig-name descname"><span class="pre">get_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.get_parameter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.get_parameter" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the parameter given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>See the docstring for <code class="docutils literal notranslate"><span class="pre">get_submodule</span></code> for a more detailed
 explanation of this method’s functionality as well as how to
@@ -4769,7 +4769,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.get_submodule">
-<span class="sig-name descname"><span class="pre">get_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L671"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.get_submodule" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L671"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.get_submodule" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the submodule given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>For example, let’s say you have an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> <code class="docutils literal notranslate"><span class="pre">A</span></code> that
 looks like this:</p>
@@ -4818,7 +4818,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.half">
-<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.half" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.half" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">half</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4836,7 +4836,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.ipu">
-<span class="sig-name descname"><span class="pre">ipu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.ipu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">ipu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.ipu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the IPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -4861,7 +4861,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assign</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2522"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assign</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2522"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy parameters and buffers from <a class="reference internal" href="#torch.nn.Module.state_dict" title="torch.nn.Module.state_dict"><code class="xref py py-attr docutils literal notranslate"><span class="pre">state_dict</span></code></a> into this module and its descendants.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">strict</span></code> is <code class="docutils literal notranslate"><span class="pre">True</span></code>, then
 the keys of <a class="reference internal" href="#torch.nn.Module.state_dict" title="torch.nn.Module.state_dict"><code class="xref py py-attr docutils literal notranslate"><span class="pre">state_dict</span></code></a> must exactly match the keys returned
@@ -4916,7 +4916,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.modules">
-<span class="sig-name descname"><span class="pre">modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2796"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2796"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over all modules in the network.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -4948,7 +4948,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.mtia">
-<span class="sig-name descname"><span class="pre">mtia</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.mtia" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mtia</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.mtia" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the MTIA.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -4973,7 +4973,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.named_buffers">
-<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.named_buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.named_buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5002,7 +5002,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.named_children">
-<span class="sig-name descname"><span class="pre">named_children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.named_children" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.named_children" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -5022,7 +5022,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.named_modules">
-<span class="sig-name descname"><span class="pre">named_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.named_modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.named_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5059,7 +5059,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.named_parameters">
-<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2681"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.named_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2681"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.named_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5089,7 +5089,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.parameters">
-<span class="sig-name descname"><span class="pre">parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2656"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2656"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module parameters.</p>
 <p>This is typically passed to an optimizer.</p>
 <dl class="field-list simple">
@@ -5116,7 +5116,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_backward_hook">
-<span class="sig-name descname"><span class="pre">register_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_backward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_backward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook on the module.</p>
 <p>This function is deprecated in favor of <a class="reference internal" href="#torch.nn.Module.register_full_backward_hook" title="torch.nn.Module.register_full_backward_hook"><code class="xref py py-meth docutils literal notranslate"><span class="pre">register_full_backward_hook()</span></code></a> and
 the behavior of this function will change in future versions.</p>
@@ -5133,7 +5133,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_buffer">
-<span class="sig-name descname"><span class="pre">register_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a buffer to the module.</p>
 <p>This is typically used to register a buffer that should not be
 considered a model parameter. For example, BatchNorm’s <code class="docutils literal notranslate"><span class="pre">running_mean</span></code>
@@ -5165,7 +5165,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_forward_hook">
-<span class="sig-name descname"><span class="pre">register_forward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">always_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_forward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_forward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">always_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_forward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a forward hook on the module.</p>
 <p>The hook will be called every time after <a class="reference internal" href="#torch.nn.Module.forward" title="torch.nn.Module.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> has computed an output.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">with_kwargs</span></code> is <code class="docutils literal notranslate"><span class="pre">False</span></code> or not specified, the input contains only
@@ -5216,7 +5216,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_forward_pre_hook">
-<span class="sig-name descname"><span class="pre">register_forward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_forward_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_forward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_forward_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a forward pre-hook on the module.</p>
 <p>The hook will be called every time before <a class="reference internal" href="#torch.nn.Module.forward" title="torch.nn.Module.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> is invoked.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">with_kwargs</span></code> is false or not specified, the input contains only
@@ -5266,7 +5266,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_full_backward_hook">
-<span class="sig-name descname"><span class="pre">register_full_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_full_backward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_full_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_full_backward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook on the module.</p>
 <p>The hook will be called every time the gradients with respect to a module are computed, and its firing rules are as follows:</p>
 <blockquote>
@@ -5323,7 +5323,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_full_backward_pre_hook">
-<span class="sig-name descname"><span class="pre">register_full_backward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_full_backward_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_full_backward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_full_backward_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward pre-hook on the module.</p>
 <p>The hook will be called every time the gradients for the module are computed.
 The hook should have the following signature:</p>
@@ -5369,7 +5369,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2312"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2312"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a post-hook to be run after module’s <code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code> is called.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, incompatible_keys) -&gt; None</p>
@@ -5399,7 +5399,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a pre-hook to be run before module’s <code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code> is called.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -&gt; None  # noqa: B950</p>
@@ -5415,7 +5415,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_module">
-<span class="sig-name descname"><span class="pre">register_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Alias for <a class="reference internal" href="#torch.nn.Module.add_module" title="torch.nn.Module.add_module"><code class="xref py py-func docutils literal notranslate"><span class="pre">add_module()</span></code></a>.</p>
 <dl class="field-list simple">
 </dl>
@@ -5423,7 +5423,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_parameter">
-<span class="sig-name descname"><span class="pre">register_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_parameter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_parameter" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a parameter to the module.</p>
 <p>The parameter can be accessed as an attribute using given name.</p>
 <dl class="field-list simple">
@@ -5442,7 +5442,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a post-hook for the <a class="reference internal" href="#torch.nn.Module.state_dict" title="torch.nn.Module.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> method.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, state_dict, prefix, local_metadata) -&gt; None</p>
@@ -5453,7 +5453,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a pre-hook for the <a class="reference internal" href="#torch.nn.Module.state_dict" title="torch.nn.Module.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> method.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, prefix, keep_vars) -&gt; None</p>
@@ -5465,7 +5465,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.requires_grad_">
-<span class="sig-name descname"><span class="pre">requires_grad_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2912"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.requires_grad_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">requires_grad_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2912"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.requires_grad_" title="Permalink to this definition">#</a></dt>
 <dd><p>Change if autograd should record operations on parameters in this module.</p>
 <p>This method sets the parameters’ <code class="xref py py-attr docutils literal notranslate"><span class="pre">requires_grad</span></code> attributes
 in-place.</p>
@@ -5489,7 +5489,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.set_extra_state">
-<span class="sig-name descname"><span class="pre">set_extra_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.set_extra_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_extra_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.set_extra_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Set extra state contained in the loaded <cite>state_dict</cite>.</p>
 <p>This function is called from <a class="reference internal" href="#torch.nn.Module.load_state_dict" title="torch.nn.Module.load_state_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> to handle any extra state
 found within the <cite>state_dict</cite>. Implement this function and a corresponding
@@ -5504,7 +5504,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.set_submodule">
-<span class="sig-name descname"><span class="pre">set_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.set_submodule" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.set_submodule" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the submodule given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -5562,7 +5562,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.share_memory">
-<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.share_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.share_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.Tensor.share_memory_.html#torch.Tensor.share_memory_" title="torch.Tensor.share_memory_"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.Tensor.share_memory_()</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5573,7 +5573,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">T_destination</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_vars</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">T_destination</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">T_destination</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_vars</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">T_destination</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.state_dict" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_vars</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Any" title="(in Python v3.14)"><span class="pre">Any</span></a><span class="p"><span class="pre">]</span></span></span></span></dt>
 <dd><p>Return a dictionary containing references to the whole state of the module.</p>
@@ -5628,7 +5628,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.to">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensor_attributes.html#torch.device" title="torch.device"><span class="pre">device</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensor_attributes.html#torch.dtype" title="torch.dtype"><span class="pre">dtype</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Self</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.to" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensor_attributes.html#torch.device" title="torch.device"><span class="pre">device</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensor_attributes.html#torch.dtype" title="torch.dtype"><span class="pre">dtype</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Self</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.to" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../tensor_attributes.html#torch.dtype" title="torch.dtype"><span class="pre">dtype</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Self</span></span></span></dt>
 <dt class="sig sig-object py">
@@ -5637,22 +5637,22 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 <p>This can be called as</p>
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memory_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.channels_last</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memory_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.channels_last</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <p>Its signature is similar to <a class="reference internal" href="torch.Tensor.to.html#torch.Tensor.to" title="torch.Tensor.to"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.Tensor.to()</span></code></a>, but only accepts
@@ -5731,7 +5731,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.to_empty">
-<span class="sig-name descname"><span class="pre">to_empty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.to_empty" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_empty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.to_empty" title="Permalink to this definition">#</a></dt>
 <dd><p>Move the parameters and buffers to the specified device without copying storage.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5753,7 +5753,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.train">
-<span class="sig-name descname"><span class="pre">train</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2872"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.train" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">train</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2872"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.train" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module in training mode.</p>
 <p>This has an effect only on certain modules. See the documentation of
 particular modules for details of their behaviors in training/evaluation
@@ -5775,7 +5775,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.type">
-<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dst_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.type" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dst_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.type" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all parameters and buffers to <code class="xref py py-attr docutils literal notranslate"><span class="pre">dst_type</span></code>.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -5796,7 +5796,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.xpu">
-<span class="sig-name descname"><span class="pre">xpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.xpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">xpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.xpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the XPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing optimizer if the module will
@@ -5821,7 +5821,7 @@ <h1>Module<a class="headerlink" href="#module" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Module.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2935"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2935"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Module.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset gradients of all model parameters.</p>
 <p>See similar function under <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.optim.Optimizer</span></code></a> for more context.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.ModuleDict.html b/2.9/generated/torch.nn.ModuleDict.html
index acb7596b0be..e9166ee4698 100644
--- a/2.9/generated/torch.nn.ModuleDict.html
+++ b/2.9/generated/torch.nn.ModuleDict.html
@@ -4404,7 +4404,7 @@
 <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ModuleDict">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ModuleDict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ModuleDict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds submodules in a dictionary.</p>
 <p><a class="reference internal" href="#torch.nn.ModuleDict" title="torch.nn.ModuleDict"><code class="xref py py-class docutils literal notranslate"><span class="pre">ModuleDict</span></code></a> can be indexed like a regular Python dictionary,
 but modules it contains are properly registered, and will be visible by all
@@ -4445,7 +4445,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleDict.clear">
-<span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L569"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.clear" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L569"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.clear" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove all items from the ModuleDict.</p>
 <dl class="field-list simple">
 </dl>
@@ -4453,7 +4453,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleDict.items">
-<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L588"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.items" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L588"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.items" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ModuleDict key/value pairs.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4464,7 +4464,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleDict.keys">
-<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.keys" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.keys" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ModuleDict keys.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4475,7 +4475,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleDict.pop">
-<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L573"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L573"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.pop" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove key from the ModuleDict and return its module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4489,7 +4489,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleDict.update">
-<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L598"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.update" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L598"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.update" title="Permalink to this definition">#</a></dt>
 <dd><p>Update the <a class="reference internal" href="#torch.nn.ModuleDict" title="torch.nn.ModuleDict"><code class="xref py py-class docutils literal notranslate"><span class="pre">ModuleDict</span></code></a> with key-value pairs from a mapping, overwriting existing keys.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4506,7 +4506,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleDict.values">
-<span class="sig-name descname"><span class="pre">values</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L593"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.values" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">values</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L593"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleDict.values" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ModuleDict values.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ModuleList.html b/2.9/generated/torch.nn.ModuleList.html
index c1db1f1809b..0b894b442f4 100644
--- a/2.9/generated/torch.nn.ModuleList.html
+++ b/2.9/generated/torch.nn.ModuleList.html
@@ -4404,7 +4404,7 @@
 <h1>ModuleList<a class="headerlink" href="#modulelist" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ModuleList">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ModuleList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleList" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ModuleList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleList" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds submodules in a list.</p>
 <p><a class="reference internal" href="#torch.nn.ModuleList" title="torch.nn.ModuleList"><code class="xref py py-class docutils literal notranslate"><span class="pre">ModuleList</span></code></a> can be indexed like a regular Python list, but
 modules it contains are properly registered, and will be visible by all
@@ -4429,7 +4429,7 @@ <h1>ModuleList<a class="headerlink" href="#modulelist" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleList.append">
-<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L465"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleList.append" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L465"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleList.append" title="Permalink to this definition">#</a></dt>
 <dd><p>Append a given module to the end of the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4443,7 +4443,7 @@ <h1>ModuleList<a class="headerlink" href="#modulelist" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleList.extend">
-<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L479"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleList.extend" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L479"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleList.extend" title="Permalink to this definition">#</a></dt>
 <dd><p>Append modules from a Python iterable to the end of the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4457,7 +4457,7 @@ <h1>ModuleList<a class="headerlink" href="#modulelist" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ModuleList.insert">
-<span class="sig-name descname"><span class="pre">insert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleList.insert" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">insert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ModuleList.insert" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert a given module before a given index in the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.MultiLabelMarginLoss.html b/2.9/generated/torch.nn.MultiLabelMarginLoss.html
index 29cdc2858e4..13e87ec0054 100644
--- a/2.9/generated/torch.nn.MultiLabelMarginLoss.html
+++ b/2.9/generated/torch.nn.MultiLabelMarginLoss.html
@@ -4404,7 +4404,7 @@
 <h1>MultiLabelMarginLoss<a class="headerlink" href="#multilabelmarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MultiLabelMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MultiLabelMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L929"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiLabelMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MultiLabelMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L929"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiLabelMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that optimizes a multi-class multi-classification
 hinge loss (margin-based loss) between input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> (a 2D mini-batch <cite>Tensor</cite>)
 and output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> (which is a 2D <cite>Tensor</cite> of target class indices).
@@ -4459,7 +4459,7 @@ <h1>MultiLabelMarginLoss<a class="headerlink" href="#multilabelmarginloss" title
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MultiLabelMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L990"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiLabelMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L990"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiLabelMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.MultiLabelSoftMarginLoss.html b/2.9/generated/torch.nn.MultiLabelSoftMarginLoss.html
index 4d2f1af55eb..3d1c45845b4 100644
--- a/2.9/generated/torch.nn.MultiLabelSoftMarginLoss.html
+++ b/2.9/generated/torch.nn.MultiLabelSoftMarginLoss.html
@@ -4404,7 +4404,7 @@
 <h1>MultiLabelSoftMarginLoss<a class="headerlink" href="#multilabelsoftmarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MultiLabelSoftMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MultiLabelSoftMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiLabelSoftMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MultiLabelSoftMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiLabelSoftMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that optimizes a multi-label one-versus-all
 loss based on max-entropy, between input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and target <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> of size
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mclose">)</span></span></span></span></span>.
@@ -4449,7 +4449,7 @@ <h1>MultiLabelSoftMarginLoss<a class="headerlink" href="#multilabelsoftmarginlos
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MultiLabelSoftMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1445"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiLabelSoftMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1445"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiLabelSoftMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.MultiMarginLoss.html b/2.9/generated/torch.nn.MultiMarginLoss.html
index b6f74343459..14474a460b7 100644
--- a/2.9/generated/torch.nn.MultiMarginLoss.html
+++ b/2.9/generated/torch.nn.MultiMarginLoss.html
@@ -4404,7 +4404,7 @@
 <h1>MultiMarginLoss<a class="headerlink" href="#multimarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MultiMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MultiMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1591"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MultiMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1591"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that optimizes a multi-class classification hinge
 loss (margin-based loss) between input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> (a 2D mini-batch <cite>Tensor</cite>) and
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> (which is a 1D tensor of target class indices,
@@ -4468,7 +4468,7 @@ <h1>MultiMarginLoss<a class="headerlink" href="#multimarginloss" title="Permalin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MultiMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.MultiheadAttention.html b/2.9/generated/torch.nn.MultiheadAttention.html
index 58850db9552..9df158a051c 100644
--- a/2.9/generated/torch.nn.MultiheadAttention.html
+++ b/2.9/generated/torch.nn.MultiheadAttention.html
@@ -4404,7 +4404,7 @@
 <h1>MultiheadAttention<a class="headerlink" href="#multiheadattention" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.MultiheadAttention">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MultiheadAttention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embed_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_heads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_bias_kv</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_zero_attn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1085"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiheadAttention" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">MultiheadAttention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embed_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_heads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_bias_kv</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_zero_attn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1085"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiheadAttention" title="Permalink to this definition">#</a></dt>
 <dd><p>Allows the model to jointly attend to information from different representation subspaces.</p>
 <p>This MultiheadAttention layer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4467,7 +4467,7 @@ <h1>MultiheadAttention<a class="headerlink" href="#multiheadattention" title="Pe
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MultiheadAttention.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">need_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">average_attn_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1252"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiheadAttention.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">need_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">average_attn_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1252"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiheadAttention.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute attention outputs using query, key, and value embeddings.</p>
 <blockquote>
 <div><p>Supports optional parameters for padding, masks and attention weights.</p>
@@ -4543,7 +4543,7 @@ <h1>MultiheadAttention<a class="headerlink" href="#multiheadattention" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.MultiheadAttention.merge_masks">
-<span class="sig-name descname"><span class="pre">merge_masks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1514"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiheadAttention.merge_masks" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">merge_masks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1514"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.MultiheadAttention.merge_masks" title="Permalink to this definition">#</a></dt>
 <dd><p>Determine mask type and combine masks if necessary.</p>
 <p>If only one mask is provided, that mask
 and the corresponding mask type will be returned. If both masks are provided, they will be both
diff --git a/2.9/generated/torch.nn.NLLLoss.html b/2.9/generated/torch.nn.NLLLoss.html
index 1e210c6c7c9..7ad7eaecd4a 100644
--- a/2.9/generated/torch.nn.NLLLoss.html
+++ b/2.9/generated/torch.nn.NLLLoss.html
@@ -4404,7 +4404,7 @@
 <h1>NLLLoss<a class="headerlink" href="#nllloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.NLLLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">NLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L135"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.NLLLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">NLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L135"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.NLLLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>The negative log likelihood loss. It is useful to train a classification
 problem with <cite>C</cite> classes.</p>
 <p>If provided, the optional argument <code class="xref py py-attr docutils literal notranslate"><span class="pre">weight</span></code> should be a 1D Tensor assigning
@@ -4511,7 +4511,7 @@ <h1>NLLLoss<a class="headerlink" href="#nllloss" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.NLLLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L255"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.NLLLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L255"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.NLLLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.PReLU.html b/2.9/generated/torch.nn.PReLU.html
index 0d084bb70ba..89d7bc7b088 100644
--- a/2.9/generated/torch.nn.PReLU.html
+++ b/2.9/generated/torch.nn.PReLU.html
@@ -4404,7 +4404,7 @@
 <h1>PReLU<a class="headerlink" href="#prelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.PReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1565"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1565"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise PReLU function.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>PReLU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>a</mi><mo>∗</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{PReLU}(x) = \max(0,x) + a * \min(0,x)
@@ -4461,7 +4461,7 @@ <h1>PReLU<a class="headerlink" href="#prelu" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PReLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1640"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PReLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1640"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PReLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4472,7 +4472,7 @@ <h1>PReLU<a class="headerlink" href="#prelu" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PReLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1634"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PReLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1634"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PReLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4483,7 +4483,7 @@ <h1>PReLU<a class="headerlink" href="#prelu" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PReLU.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1628"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PReLU.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1628"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PReLU.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.PairwiseDistance.html b/2.9/generated/torch.nn.PairwiseDistance.html
index e87db9f2405..6821c52ee7b 100644
--- a/2.9/generated/torch.nn.PairwiseDistance.html
+++ b/2.9/generated/torch.nn.PairwiseDistance.html
@@ -4404,7 +4404,7 @@
 <h1>PairwiseDistance<a class="headerlink" href="#pairwisedistance" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.PairwiseDistance">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PairwiseDistance</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/distance.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PairwiseDistance" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PairwiseDistance</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/distance.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PairwiseDistance" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the pairwise distance between input vectors, or between columns of input matrices.</p>
 <p>Distances are computed using <code class="docutils literal notranslate"><span class="pre">p</span></code>-norm, with constant <code class="docutils literal notranslate"><span class="pre">eps</span></code> added to avoid division by zero
 if <code class="docutils literal notranslate"><span class="pre">p</span></code> is negative, i.e.:</p>
@@ -4444,7 +4444,7 @@ <h1>PairwiseDistance<a class="headerlink" href="#pairwisedistance" title="Permal
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PairwiseDistance.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/distance.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PairwiseDistance.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/distance.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PairwiseDistance.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ParameterDict.html b/2.9/generated/torch.nn.ParameterDict.html
index 07150a5f226..abfdd6c3440 100644
--- a/2.9/generated/torch.nn.ParameterDict.html
+++ b/2.9/generated/torch.nn.ParameterDict.html
@@ -4404,7 +4404,7 @@
 <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ParameterDict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L785"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ParameterDict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L785"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds parameters in a dictionary.</p>
 <p>ParameterDict can be indexed like a regular Python dictionary, but Parameters it
 contains are properly registered, and will be visible by all Module methods.
@@ -4442,7 +4442,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.clear">
-<span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L895"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.clear" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L895"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.clear" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove all items from the ParameterDict.</p>
 <dl class="field-list simple">
 </dl>
@@ -4450,7 +4450,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.copy">
-<span class="sig-name descname"><span class="pre">copy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L871"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.copy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">copy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L871"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.copy" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a copy of this <a class="reference internal" href="#torch.nn.ParameterDict" title="torch.nn.ParameterDict"><code class="xref py py-class docutils literal notranslate"><span class="pre">ParameterDict</span></code></a> instance.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4461,7 +4461,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.fromkeys">
-<span class="sig-name descname"><span class="pre">fromkeys</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L928"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.fromkeys" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fromkeys</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L928"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.fromkeys" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a new ParameterDict with the keys provided.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4478,7 +4478,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.get">
-<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L919"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.get" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L919"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.get" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the parameter associated with key if present. Otherwise return default if provided, None if not.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4495,7 +4495,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.items">
-<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L943"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.items" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L943"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.items" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ParameterDict key/value pairs.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4506,7 +4506,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.keys">
-<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L939"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.keys" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L939"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.keys" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ParameterDict keys.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4517,7 +4517,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.pop">
-<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L900"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L900"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.pop" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove key from the ParameterDict and return its parameter.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4531,7 +4531,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.popitem">
-<span class="sig-name descname"><span class="pre">popitem</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.popitem" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">popitem</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.popitem" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove and return the last inserted <cite>(key, parameter)</cite> pair from the ParameterDict.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4542,7 +4542,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.setdefault">
-<span class="sig-name descname"><span class="pre">setdefault</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.setdefault" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">setdefault</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.setdefault" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the default for a key in the Parameterdict.</p>
 <p>If key is in the ParameterDict, return its value.
 If not, insert <cite>key</cite> with a parameter <cite>default</cite> and return <cite>default</cite>.
@@ -4562,7 +4562,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.update">
-<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.update" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.update" title="Permalink to this definition">#</a></dt>
 <dd><p>Update the <a class="reference internal" href="#torch.nn.ParameterDict" title="torch.nn.ParameterDict"><code class="xref py py-class docutils literal notranslate"><span class="pre">ParameterDict</span></code></a> with key-value pairs from <code class="docutils literal notranslate"><span class="pre">parameters</span></code>, overwriting existing keys.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4580,7 +4580,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterDict.values">
-<span class="sig-name descname"><span class="pre">values</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L947"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.values" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">values</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L947"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterDict.values" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ParameterDict values.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ParameterList.html b/2.9/generated/torch.nn.ParameterList.html
index d193c223a70..1134526c2c2 100644
--- a/2.9/generated/torch.nn.ParameterList.html
+++ b/2.9/generated/torch.nn.ParameterList.html
@@ -4404,7 +4404,7 @@
 <h1>ParameterList<a class="headerlink" href="#parameterlist" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ParameterList">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ParameterList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L638"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterList" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ParameterList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L638"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterList" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds parameters in a list.</p>
 <p><a class="reference internal" href="#torch.nn.ParameterList" title="torch.nn.ParameterList"><code class="xref py py-class docutils literal notranslate"><span class="pre">ParameterList</span></code></a> can be used like a regular Python
 list, but Tensors that are <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> are properly registered,
@@ -4434,7 +4434,7 @@ <h1>ParameterList<a class="headerlink" href="#parameterlist" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterList.append">
-<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L725"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterList.append" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L725"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterList.append" title="Permalink to this definition">#</a></dt>
 <dd><p>Append a given value at the end of the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4448,7 +4448,7 @@ <h1>ParameterList<a class="headerlink" href="#parameterlist" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterList.extend">
-<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterList.extend" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterList.extend" title="Permalink to this definition">#</a></dt>
 <dd><p>Append values from a Python iterable to the end of the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4462,7 +4462,7 @@ <h1>ParameterList<a class="headerlink" href="#parameterlist" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ParameterList.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterList.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ParameterList.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.PixelShuffle.html b/2.9/generated/torch.nn.PixelShuffle.html
index e6bbfa765bb..aa4f0fbaf8f 100644
--- a/2.9/generated/torch.nn.PixelShuffle.html
+++ b/2.9/generated/torch.nn.PixelShuffle.html
@@ -4404,7 +4404,7 @@
 <h1>PixelShuffle<a class="headerlink" href="#pixelshuffle" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.PixelShuffle">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PixelShuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">upscale_factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelShuffle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PixelShuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">upscale_factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelShuffle" title="Permalink to this definition">#</a></dt>
 <dd><p>Rearrange elements in a tensor according to an upscaling factor.</p>
 <p>Rearranges elements in a tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mo>∗</mo><mo separator="true">,</mo><mi>C</mi><mo>×</mo><msup><mi>r</mi><mn>2</mn></msup><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(*, C \times r^2, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord">∗</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1.0641em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8141em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>
 to a tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mo>∗</mo><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>H</mi><mo>×</mo><mi>r</mi><mo separator="true">,</mo><mi>W</mi><mo>×</mo><mi>r</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(*, C, H \times r, W \times r)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord">∗</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8778em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="mclose">)</span></span></span></span></span>, where r is an upscale factor.</p>
@@ -4444,7 +4444,7 @@ <h1>PixelShuffle<a class="headerlink" href="#pixelshuffle" title="Permalink to t
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PixelShuffle.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelShuffle.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelShuffle.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4455,7 +4455,7 @@ <h1>PixelShuffle<a class="headerlink" href="#pixelshuffle" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PixelShuffle.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelShuffle.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelShuffle.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.PixelUnshuffle.html b/2.9/generated/torch.nn.PixelUnshuffle.html
index a29efd166cb..3524b9d6d64 100644
--- a/2.9/generated/torch.nn.PixelUnshuffle.html
+++ b/2.9/generated/torch.nn.PixelUnshuffle.html
@@ -4404,7 +4404,7 @@
 <h1>PixelUnshuffle<a class="headerlink" href="#pixelunshuffle" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.PixelUnshuffle">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PixelUnshuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">downscale_factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelUnshuffle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PixelUnshuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">downscale_factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelUnshuffle" title="Permalink to this definition">#</a></dt>
 <dd><p>Reverse the PixelShuffle operation.</p>
 <p>Reverses the <a class="reference internal" href="torch.nn.PixelShuffle.html#torch.nn.PixelShuffle" title="torch.nn.PixelShuffle"><code class="xref py py-class docutils literal notranslate"><span class="pre">PixelShuffle</span></code></a> operation by rearranging elements
 in a tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mo>∗</mo><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>H</mi><mo>×</mo><mi>r</mi><mo separator="true">,</mo><mi>W</mi><mo>×</mo><mi>r</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(*, C, H \times r, W \times r)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord">∗</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8778em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="mclose">)</span></span></span></span></span> to a tensor of shape
@@ -4443,7 +4443,7 @@ <h1>PixelUnshuffle<a class="headerlink" href="#pixelunshuffle" title="Permalink
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PixelUnshuffle.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L123"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelUnshuffle.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L123"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelUnshuffle.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4454,7 +4454,7 @@ <h1>PixelUnshuffle<a class="headerlink" href="#pixelunshuffle" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PixelUnshuffle.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelUnshuffle.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PixelUnshuffle.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.PoissonNLLLoss.html b/2.9/generated/torch.nn.PoissonNLLLoss.html
index 569fca7e9cd..a45448606ff 100644
--- a/2.9/generated/torch.nn.PoissonNLLLoss.html
+++ b/2.9/generated/torch.nn.PoissonNLLLoss.html
@@ -4404,7 +4404,7 @@
 <h1>PoissonNLLLoss<a class="headerlink" href="#poissonnllloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.PoissonNLLLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PoissonNLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PoissonNLLLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">PoissonNLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PoissonNLLLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Negative log likelihood loss with Poisson distribution of target.</p>
 <p>The loss can be described as:</p>
 <div class="math">
@@ -4465,7 +4465,7 @@ <h1>PoissonNLLLoss<a class="headerlink" href="#poissonnllloss" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.PoissonNLLLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PoissonNLLLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.PoissonNLLLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.RMSNorm.html b/2.9/generated/torch.nn.RMSNorm.html
index 257d4e78ede..01fda3a8496 100644
--- a/2.9/generated/torch.nn.RMSNorm.html
+++ b/2.9/generated/torch.nn.RMSNorm.html
@@ -4404,7 +4404,7 @@
 <h1>RMSNorm<a class="headerlink" href="#rmsnorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.RMSNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RMSNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L333"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RMSNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RMSNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L333"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RMSNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Root Mean Square Layer Normalization over a mini-batch of inputs.</p>
 <p>This layer implements the operation as described in
 the paper <a class="reference external" href="https://arxiv.org/pdf/1910.07467.pdf">Root Mean Square Layer Normalization</a></p>
@@ -4453,7 +4453,7 @@ <h1>RMSNorm<a class="headerlink" href="#rmsnorm" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.RMSNorm.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RMSNorm.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RMSNorm.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4464,7 +4464,7 @@ <h1>RMSNorm<a class="headerlink" href="#rmsnorm" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.RMSNorm.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RMSNorm.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RMSNorm.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4475,7 +4475,7 @@ <h1>RMSNorm<a class="headerlink" href="#rmsnorm" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.RMSNorm.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L403"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RMSNorm.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L403"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RMSNorm.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in __init__.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.RNN.html b/2.9/generated/torch.nn.RNN.html
index 91ff25b2414..6a1fb393992 100644
--- a/2.9/generated/torch.nn.RNN.html
+++ b/2.9/generated/torch.nn.RNN.html
@@ -4404,7 +4404,7 @@
 <h1>RNN<a class="headerlink" href="#rnn" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.RNN">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RNN</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNN" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RNN</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNN" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a multi-layer Elman RNN with <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>tanh</mi><mo>⁡</mo></mrow><annotation encoding="application/x-tex">\tanh</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mop">tanh</span></span></span></span></span> or <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>ReLU</mtext></mrow><annotation encoding="application/x-tex">\text{ReLU}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord text"><span class="mord">ReLU</span></span></span></span></span></span>
 non-linearity to an input sequence. For each element in the input sequence,
 each layer computes the following function:</p>
@@ -4587,7 +4587,7 @@ <h1>RNN<a class="headerlink" href="#rnn" title="Permalink to this heading">#</a>
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.RNN.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">hx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L654"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNN.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">hx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L654"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNN.forward" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="torch.nn.utils.rnn.PackedSequence.html#torch.nn.utils.rnn.PackedSequence" title="torch.nn.utils.rnn.PackedSequence"><span class="pre">PackedSequence</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">hx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="torch.nn.utils.rnn.PackedSequence.html#torch.nn.utils.rnn.PackedSequence" title="torch.nn.utils.rnn.PackedSequence"><span class="pre">torch.nn.utils.rnn.PackedSequence</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span></dt>
 <dd><p>Runs the forward pass.</p>
diff --git a/2.9/generated/torch.nn.RNNBase.html b/2.9/generated/torch.nn.RNNBase.html
index 07a59bc5e7c..f6ded866743 100644
--- a/2.9/generated/torch.nn.RNNBase.html
+++ b/2.9/generated/torch.nn.RNNBase.html
@@ -4404,7 +4404,7 @@
 <h1>RNNBase<a class="headerlink" href="#rnnbase" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.RNNBase">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RNNBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proj_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNNBase" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RNNBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proj_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNNBase" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class for RNN modules (RNN, LSTM, GRU).</p>
 <p>Implements aspects of RNNs shared by the RNN, LSTM, and GRU classes, such as module initialization
 and utility methods for parameter storage management.</p>
@@ -4420,7 +4420,7 @@ <h1>RNNBase<a class="headerlink" href="#rnnbase" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.RNNBase.flatten_parameters">
-<span class="sig-name descname"><span class="pre">flatten_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNNBase.flatten_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">flatten_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNNBase.flatten_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset parameter data pointer so that they can use faster code paths.</p>
 <p>Right now, this works only if the module is on the GPU and cuDNN is enabled.
 Otherwise, it’s a no-op.</p>
diff --git a/2.9/generated/torch.nn.RNNCell.html b/2.9/generated/torch.nn.RNNCell.html
index 486363dacde..44fb46454f4 100644
--- a/2.9/generated/torch.nn.RNNCell.html
+++ b/2.9/generated/torch.nn.RNNCell.html
@@ -4404,7 +4404,7 @@
 <h1>RNNCell<a class="headerlink" href="#rnncell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.RNNCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RNNCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L1492"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNNCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RNNCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L1492"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RNNCell" title="Permalink to this definition">#</a></dt>
 <dd><p>An Elman RNN cell with tanh or ReLU non-linearity.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><msup><mi>h</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo>=</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>h</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>h</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>h</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>h</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">h&#x27; = \tanh(W_{ih} x + b_{ih}  +  W_{hh} h + b_{hh})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8019em;"></span><span class="mord"><span class="mord mathnormal">h</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8019em;"><span style="top:-3.113em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">′</span></span></span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">tanh</span><span class="mopen">(</span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">ih</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8444em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">b</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">ih</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8444em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">hh</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mord mathnormal">h</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal">b</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">hh</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span></div><p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">nonlinearity</span></code> is <cite>‘relu’</cite>, then ReLU is used in place of tanh.</p>
diff --git a/2.9/generated/torch.nn.RReLU.html b/2.9/generated/torch.nn.RReLU.html
index d02fff81b46..6834b57a7bb 100644
--- a/2.9/generated/torch.nn.RReLU.html
+++ b/2.9/generated/torch.nn.RReLU.html
@@ -4404,7 +4404,7 @@
 <h1>RReLU<a class="headerlink" href="#rrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.RReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lower</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.125</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">upper</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3333333333333333</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">RReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lower</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.125</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">upper</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3333333333333333</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the randomized leaky rectified linear unit function, element-wise.</p>
 <p>Method described in the paper:
 <a class="reference external" href="https://arxiv.org/abs/1505.00853">Empirical Evaluation of Rectified Activations in Convolutional Network</a>.</p>
@@ -4444,7 +4444,7 @@ <h1>RReLU<a class="headerlink" href="#rrelu" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.RReLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RReLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RReLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4455,7 +4455,7 @@ <h1>RReLU<a class="headerlink" href="#rrelu" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.RReLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RReLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.RReLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ReLU.html b/2.9/generated/torch.nn.ReLU.html
index 5163f41496f..aad12c0ed73 100644
--- a/2.9/generated/torch.nn.ReLU.html
+++ b/2.9/generated/torch.nn.ReLU.html
@@ -4404,7 +4404,7 @@
 <h1>ReLU<a class="headerlink" href="#relu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the rectified linear unit function element-wise.</p>
 <p><span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>ReLU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mo stretchy="false">(</mo><mi>x</mi><msup><mo stretchy="false">)</mo><mo>+</mo></msup><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{ReLU}(x) = (x)^+ = \max(0, x)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">ReLU</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.0213em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose"><span class="mclose">)</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.7713em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mbin mtight">+</span></span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span></span></p>
 <dl class="field-list simple">
@@ -4435,7 +4435,7 @@ <h1>ReLU<a class="headerlink" href="#relu" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ReLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4446,7 +4446,7 @@ <h1>ReLU<a class="headerlink" href="#relu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ReLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ReLU6.html b/2.9/generated/torch.nn.ReLU6.html
index 04d3f1837f2..c73956dadec 100644
--- a/2.9/generated/torch.nn.ReLU6.html
+++ b/2.9/generated/torch.nn.ReLU6.html
@@ -4404,7 +4404,7 @@
 <h1>ReLU6<a class="headerlink" href="#relu6" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ReLU6">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReLU6</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU6" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReLU6</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU6" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the ReLU6 function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>ReLU6</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo separator="true">,</mo><mn>6</mn><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{ReLU6}(x) = \min(\max(0,x), 6)
@@ -4430,7 +4430,7 @@ <h1>ReLU6<a class="headerlink" href="#relu6" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ReLU6.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU6.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReLU6.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ReflectionPad1d.html b/2.9/generated/torch.nn.ReflectionPad1d.html
index a773e44ec03..2fe8608a223 100644
--- a/2.9/generated/torch.nn.ReflectionPad1d.html
+++ b/2.9/generated/torch.nn.ReflectionPad1d.html
@@ -4404,7 +4404,7 @@
 <h1>ReflectionPad1d<a class="headerlink" href="#reflectionpad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ReflectionPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReflectionPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReflectionPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using the reflection of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.ReflectionPad2d.html b/2.9/generated/torch.nn.ReflectionPad2d.html
index 0298f22cb4a..1a8fe9bd229 100644
--- a/2.9/generated/torch.nn.ReflectionPad2d.html
+++ b/2.9/generated/torch.nn.ReflectionPad2d.html
@@ -4404,7 +4404,7 @@
 <h1>ReflectionPad2d<a class="headerlink" href="#reflectionpad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ReflectionPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReflectionPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReflectionPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using the reflection of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.ReflectionPad3d.html b/2.9/generated/torch.nn.ReflectionPad3d.html
index 0f0878f3d9e..e80e6ff55dc 100644
--- a/2.9/generated/torch.nn.ReflectionPad3d.html
+++ b/2.9/generated/torch.nn.ReflectionPad3d.html
@@ -4404,7 +4404,7 @@
 <h1>ReflectionPad3d<a class="headerlink" href="#reflectionpad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ReflectionPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L472"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReflectionPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L472"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReflectionPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using the reflection of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.ReplicationPad1d.html b/2.9/generated/torch.nn.ReplicationPad1d.html
index 3603e687cd3..6b96f18c146 100644
--- a/2.9/generated/torch.nn.ReplicationPad1d.html
+++ b/2.9/generated/torch.nn.ReplicationPad1d.html
@@ -4404,7 +4404,7 @@
 <h1>ReplicationPad1d<a class="headerlink" href="#replicationpad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ReplicationPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReplicationPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReplicationPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using replication of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.ReplicationPad2d.html b/2.9/generated/torch.nn.ReplicationPad2d.html
index b6c5927910f..38827cc5ebf 100644
--- a/2.9/generated/torch.nn.ReplicationPad2d.html
+++ b/2.9/generated/torch.nn.ReplicationPad2d.html
@@ -4404,7 +4404,7 @@
 <h1>ReplicationPad2d<a class="headerlink" href="#replicationpad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ReplicationPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReplicationPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReplicationPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using replication of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.ReplicationPad3d.html b/2.9/generated/torch.nn.ReplicationPad3d.html
index e6d9c7236cb..79e5fbe9796 100644
--- a/2.9/generated/torch.nn.ReplicationPad3d.html
+++ b/2.9/generated/torch.nn.ReplicationPad3d.html
@@ -4404,7 +4404,7 @@
 <h1>ReplicationPad3d<a class="headerlink" href="#replicationpad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ReplicationPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReplicationPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ReplicationPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using replication of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.SELU.html b/2.9/generated/torch.nn.SELU.html
index 46159694c28..1fa233b420d 100644
--- a/2.9/generated/torch.nn.SELU.html
+++ b/2.9/generated/torch.nn.SELU.html
@@ -4404,7 +4404,7 @@
 <h1>SELU<a class="headerlink" href="#selu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.SELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SELU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the SELU function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>SELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mtext>scale</mtext><mo>∗</mo><mo stretchy="false">(</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>α</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{SELU}(x) = \text{scale} * (\max(0,x) + \min(0, \alpha * (\exp(x) - 1)))
@@ -4440,7 +4440,7 @@ <h1>SELU<a class="headerlink" href="#selu" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.SELU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L726"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SELU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L726"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SELU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4451,7 +4451,7 @@ <h1>SELU<a class="headerlink" href="#selu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.SELU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L720"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SELU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L720"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SELU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Sequential.html b/2.9/generated/torch.nn.Sequential.html
index 771a34eb10d..ca27b3654d1 100644
--- a/2.9/generated/torch.nn.Sequential.html
+++ b/2.9/generated/torch.nn.Sequential.html
@@ -4404,7 +4404,7 @@
 <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Sequential">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Sequential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Sequential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Sequential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">arg</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.html#collections.OrderedDict" title="(in Python v3.14)"><span class="pre">OrderedDict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span></dt>
 <dd><p>A sequential container.</p>
@@ -4450,7 +4450,7 @@ <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Sequential.append">
-<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L253"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.append" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L253"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.append" title="Permalink to this definition">#</a></dt>
 <dd><p>Append a given module to the end.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4475,7 +4475,7 @@ <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Sequential.extend">
-<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequential</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.extend" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequential</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.extend" title="Permalink to this definition">#</a></dt>
 <dd><p>Extends the current Sequential container with layers from another Sequential container.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4502,13 +4502,13 @@ <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Sequential.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Sequential.insert">
-<span class="sig-name descname"><span class="pre">insert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.insert" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">insert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.insert" title="Permalink to this definition">#</a></dt>
 <dd><p>Inserts a module into the Sequential container at the specified index.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4536,7 +4536,7 @@ <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Sequential.pop">
-<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sequential.pop" title="Permalink to this definition">#</a></dt>
 <dd><p>Pop <code class="docutils literal notranslate"><span class="pre">key</span></code> from self.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.SiLU.html b/2.9/generated/torch.nn.SiLU.html
index 4d7d6f72746..d0190a89194 100644
--- a/2.9/generated/torch.nn.SiLU.html
+++ b/2.9/generated/torch.nn.SiLU.html
@@ -4404,7 +4404,7 @@
 <h1>SiLU<a class="headerlink" href="#silu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.SiLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SiLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L433"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SiLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SiLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L433"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SiLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Sigmoid Linear Unit (SiLU) function, element-wise.</p>
 <p>The SiLU function is also known as the swish function.</p>
 <div class="math">
@@ -4437,7 +4437,7 @@ <h1>SiLU<a class="headerlink" href="#silu" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.SiLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L475"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SiLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L475"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SiLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4448,7 +4448,7 @@ <h1>SiLU<a class="headerlink" href="#silu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.SiLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L469"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SiLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L469"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SiLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Sigmoid.html b/2.9/generated/torch.nn.Sigmoid.html
index 0912788e143..261408963b8 100644
--- a/2.9/generated/torch.nn.Sigmoid.html
+++ b/2.9/generated/torch.nn.Sigmoid.html
@@ -4404,7 +4404,7 @@
 <h1>Sigmoid<a class="headerlink" href="#sigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Sigmoid">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Sigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L335"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sigmoid" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Sigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L335"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Sigmoid function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>Sigmoid</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mn>1</mn><mrow><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow></mfrac></mrow><annotation encoding="application/x-tex">\text{Sigmoid}(x) = \sigma(x) = \frac{1}{1 + \exp(-x)}
@@ -4427,7 +4427,7 @@ <h1>Sigmoid<a class="headerlink" href="#sigmoid" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Sigmoid.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L355"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sigmoid.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L355"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Sigmoid.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.SmoothL1Loss.html b/2.9/generated/torch.nn.SmoothL1Loss.html
index 9ee9d14781c..dc5c0ab5f03 100644
--- a/2.9/generated/torch.nn.SmoothL1Loss.html
+++ b/2.9/generated/torch.nn.SmoothL1Loss.html
@@ -4404,7 +4404,7 @@
 <h1>SmoothL1Loss<a class="headerlink" href="#smoothl1loss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.SmoothL1Loss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SmoothL1Loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L995"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SmoothL1Loss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SmoothL1Loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L995"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SmoothL1Loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that uses a squared term if the absolute
 element-wise error falls below beta and an L1 term otherwise.
 It is less sensitive to outliers than <a class="reference internal" href="torch.nn.MSELoss.html#torch.nn.MSELoss" title="torch.nn.MSELoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.MSELoss</span></code></a> and in some cases
@@ -4481,7 +4481,7 @@ <h1>SmoothL1Loss<a class="headerlink" href="#smoothl1loss" title="Permalink to t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.SmoothL1Loss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1075"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SmoothL1Loss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1075"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SmoothL1Loss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.SoftMarginLoss.html b/2.9/generated/torch.nn.SoftMarginLoss.html
index 4b966937616..013ca825c21 100644
--- a/2.9/generated/torch.nn.SoftMarginLoss.html
+++ b/2.9/generated/torch.nn.SoftMarginLoss.html
@@ -4404,7 +4404,7 @@
 <h1>SoftMarginLoss<a class="headerlink" href="#softmarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.SoftMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SoftMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1142"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SoftMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SoftMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1142"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SoftMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that optimizes a two-class classification
 logistic loss between input tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and target tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span>
 (containing 1 or -1).</p>
@@ -4443,7 +4443,7 @@ <h1>SoftMarginLoss<a class="headerlink" href="#softmarginloss" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.SoftMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1180"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SoftMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1180"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SoftMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Softmax.html b/2.9/generated/torch.nn.Softmax.html
index cdeafc3bd02..ff4d385d76c 100644
--- a/2.9/generated/torch.nn.Softmax.html
+++ b/2.9/generated/torch.nn.Softmax.html
@@ -4404,7 +4404,7 @@
 <h1>Softmax<a class="headerlink" href="#softmax" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Softmax">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1755"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1755"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Softmax function to an n-dimensional input Tensor.</p>
 <p>Rescales them so that the elements of the n-dimensional output Tensor
 lie in the range [0,1] and sum to 1.</p>
@@ -4449,7 +4449,7 @@ <h1>Softmax<a class="headerlink" href="#softmax" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softmax.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1813"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1813"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4460,7 +4460,7 @@ <h1>Softmax<a class="headerlink" href="#softmax" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softmax.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Softmax2d.html b/2.9/generated/torch.nn.Softmax2d.html
index b7d96492376..e55263004b2 100644
--- a/2.9/generated/torch.nn.Softmax2d.html
+++ b/2.9/generated/torch.nn.Softmax2d.html
@@ -4404,7 +4404,7 @@
 <h1>Softmax2d<a class="headerlink" href="#softmax2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Softmax2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softmax2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1820"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softmax2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1820"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies SoftMax over features to each spatial location.</p>
 <p>When given an image of <code class="docutils literal notranslate"><span class="pre">Channels</span> <span class="pre">x</span> <span class="pre">Height</span> <span class="pre">x</span> <span class="pre">Width</span></code>, it will
 apply <cite>Softmax</cite> to each location <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>C</mi><mi>h</mi><mi>a</mi><mi>n</mi><mi>n</mi><mi>e</mi><mi>l</mi><mi>s</mi><mo separator="true">,</mo><msub><mi>h</mi><mi>i</mi></msub><mo separator="true">,</mo><msub><mi>w</mi><mi>j</mi></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(Channels, h_i, w_j)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1.0361em;vertical-align:-0.2861em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mord mathnormal">hann</span><span class="mord mathnormal">e</span><span class="mord mathnormal" style="margin-right:0.01968em;">l</span><span class="mord mathnormal">s</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal">h</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3117em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">i</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02691em;">w</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3117em;"><span style="top:-2.55em;margin-left:-0.0269em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight" style="margin-right:0.05724em;">j</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2861em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span></p>
@@ -4433,7 +4433,7 @@ <h1>Softmax2d<a class="headerlink" href="#softmax2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softmax2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1842"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1842"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmax2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Softmin.html b/2.9/generated/torch.nn.Softmin.html
index d3e8539935f..86811010781 100644
--- a/2.9/generated/torch.nn.Softmin.html
+++ b/2.9/generated/torch.nn.Softmin.html
@@ -4404,7 +4404,7 @@
 <h1>Softmin<a class="headerlink" href="#softmin" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Softmin">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softmin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1699"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmin" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softmin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1699"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmin" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Softmin function to an n-dimensional input Tensor.</p>
 <p>Rescales them so that the elements of the n-dimensional output Tensor
 lie in the range <cite>[0, 1]</cite> and sum to 1.</p>
@@ -4441,7 +4441,7 @@ <h1>Softmin<a class="headerlink" href="#softmin" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softmin.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1748"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmin.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1748"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmin.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4452,7 +4452,7 @@ <h1>Softmin<a class="headerlink" href="#softmin" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softmin.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1742"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmin.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1742"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softmin.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Softplus.html b/2.9/generated/torch.nn.Softplus.html
index 6562f73bee8..f8dec8fe9d9 100644
--- a/2.9/generated/torch.nn.Softplus.html
+++ b/2.9/generated/torch.nn.Softplus.html
@@ -4404,7 +4404,7 @@
 <h1>Softplus<a class="headerlink" href="#softplus" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Softplus">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softplus</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L958"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softplus" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softplus</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L958"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softplus" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Softplus function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>Softplus</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mn>1</mn><mi>β</mi></mfrac><mo>∗</mo><mi>log</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>β</mi><mo>∗</mo><mi>x</mi><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{Softplus}(x) = \frac{1}{\beta} * \log(1 + \exp(\beta * x))
@@ -4437,7 +4437,7 @@ <h1>Softplus<a class="headerlink" href="#softplus" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softplus.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1002"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softplus.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1002"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softplus.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4448,7 +4448,7 @@ <h1>Softplus<a class="headerlink" href="#softplus" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softplus.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L996"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softplus.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L996"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softplus.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Softshrink.html b/2.9/generated/torch.nn.Softshrink.html
index 3c2cb1b9f8c..064062d7270 100644
--- a/2.9/generated/torch.nn.Softshrink.html
+++ b/2.9/generated/torch.nn.Softshrink.html
@@ -4404,7 +4404,7 @@
 <h1>Softshrink<a class="headerlink" href="#softshrink" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Softshrink">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1009"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softshrink" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1009"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softshrink" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the soft shrinkage function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>SoftShrinkage</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mrow><mo fence="true">{</mo><mtable rowspacing="0.36em" columnalign="left left" columnspacing="1em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>x</mi><mo>−</mo><mi>λ</mi><mo separator="true">,</mo></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mtext> if </mtext><mi>x</mi><mo>&gt;</mo><mi>λ</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>x</mi><mo>+</mo><mi>λ</mi><mo separator="true">,</mo></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mtext> if </mtext><mi>x</mi><mo>&lt;</mo><mo>−</mo><mi>λ</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mn>0</mn><mo separator="true">,</mo></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mtext> otherwise </mtext></mstyle></mtd></mtr></mtable></mrow></mrow><annotation encoding="application/x-tex">\text{SoftShrinkage}(x) =
@@ -4435,7 +4435,7 @@ <h1>Softshrink<a class="headerlink" href="#softshrink" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softshrink.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1049"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softshrink.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1049"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softshrink.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4446,7 +4446,7 @@ <h1>Softshrink<a class="headerlink" href="#softshrink" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softshrink.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softshrink.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softshrink.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Softsign.html b/2.9/generated/torch.nn.Softsign.html
index 42e30e5d9e2..38721a0290f 100644
--- a/2.9/generated/torch.nn.Softsign.html
+++ b/2.9/generated/torch.nn.Softsign.html
@@ -4404,7 +4404,7 @@
 <h1>Softsign<a class="headerlink" href="#softsign" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Softsign">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softsign</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1647"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softsign" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Softsign</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1647"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softsign" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise Softsign function.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>SoftSign</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mi>x</mi><mrow><mn>1</mn><mo>+</mo><mi mathvariant="normal">∣</mi><mi>x</mi><mi mathvariant="normal">∣</mi></mrow></mfrac></mrow><annotation encoding="application/x-tex">\text{SoftSign}(x) = \frac{x}{ 1 + |x|}
@@ -4427,7 +4427,7 @@ <h1>Softsign<a class="headerlink" href="#softsign" title="Permalink to this head
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Softsign.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softsign.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Softsign.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.SyncBatchNorm.html b/2.9/generated/torch.nn.SyncBatchNorm.html
index def65badf8c..d99089e7fed 100644
--- a/2.9/generated/torch.nn.SyncBatchNorm.html
+++ b/2.9/generated/torch.nn.SyncBatchNorm.html
@@ -4404,7 +4404,7 @@
 <h1>SyncBatchNorm<a class="headerlink" href="#syncbatchnorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.SyncBatchNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SyncBatchNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SyncBatchNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">SyncBatchNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SyncBatchNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Batch Normalization over a N-Dimensional input.</p>
 <p>The N-D input is a mini-batch of [N-2]D inputs with additional channel dimension) as described in the paper
 <a class="reference external" href="https://arxiv.org/abs/1502.03167">Batch Normalization: Accelerating Deep Network Training by Reducing
@@ -4516,7 +4516,7 @@ <h1>SyncBatchNorm<a class="headerlink" href="#syncbatchnorm" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.SyncBatchNorm.convert_sync_batchnorm">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">convert_sync_batchnorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L828"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SyncBatchNorm.convert_sync_batchnorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">convert_sync_batchnorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L828"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SyncBatchNorm.convert_sync_batchnorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts all <code class="xref py py-attr docutils literal notranslate"><span class="pre">BatchNorm*D</span></code> layers in the model to <a class="reference internal" href="#torch.nn.SyncBatchNorm" title="torch.nn.SyncBatchNorm"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.SyncBatchNorm</span></code></a> layers.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4555,7 +4555,7 @@ <h1>SyncBatchNorm<a class="headerlink" href="#syncbatchnorm" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.SyncBatchNorm.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SyncBatchNorm.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.SyncBatchNorm.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Tanh.html b/2.9/generated/torch.nn.Tanh.html
index da8a611339e..44ca0e36025 100644
--- a/2.9/generated/torch.nn.Tanh.html
+++ b/2.9/generated/torch.nn.Tanh.html
@@ -4404,7 +4404,7 @@
 <h1>Tanh<a class="headerlink" href="#tanh" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Tanh">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Tanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Tanh" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Tanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Tanh" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Hyperbolic Tangent (Tanh) function element-wise.</p>
 <p>Tanh is defined as:</p>
 <div class="math">
@@ -4428,7 +4428,7 @@ <h1>Tanh<a class="headerlink" href="#tanh" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Tanh.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Tanh.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Tanh.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Tanhshrink.html b/2.9/generated/torch.nn.Tanhshrink.html
index 045c28b7366..c2eaa38243b 100644
--- a/2.9/generated/torch.nn.Tanhshrink.html
+++ b/2.9/generated/torch.nn.Tanhshrink.html
@@ -4404,7 +4404,7 @@
 <h1>Tanhshrink<a class="headerlink" href="#tanhshrink" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Tanhshrink">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Tanhshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1673"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Tanhshrink" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Tanhshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1673"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Tanhshrink" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise Tanhshrink function.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>Tanhshrink</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>x</mi><mo>−</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{Tanhshrink}(x) = x - \tanh(x)
@@ -4427,7 +4427,7 @@ <h1>Tanhshrink<a class="headerlink" href="#tanhshrink" title="Permalink to this
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Tanhshrink.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1692"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Tanhshrink.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1692"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Tanhshrink.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Threshold.html b/2.9/generated/torch.nn.Threshold.html
index 3999d0aacac..37b0228f8c2 100644
--- a/2.9/generated/torch.nn.Threshold.html
+++ b/2.9/generated/torch.nn.Threshold.html
@@ -4404,7 +4404,7 @@
 <h1>Threshold<a class="headerlink" href="#threshold" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Threshold">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Threshold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Threshold" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Threshold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Threshold" title="Permalink to this definition">#</a></dt>
 <dd><p>Thresholds each element of the input Tensor.</p>
 <p>Threshold is defined as:</p>
 <div class="math">
@@ -4439,7 +4439,7 @@ <h1>Threshold<a class="headerlink" href="#threshold" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Threshold.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Threshold.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Threshold.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4450,7 +4450,7 @@ <h1>Threshold<a class="headerlink" href="#threshold" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Threshold.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L91"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Threshold.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L91"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Threshold.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Transformer.html b/2.9/generated/torch.nn.Transformer.html
index d2d383f1c47..0204ff36d15 100644
--- a/2.9/generated/torch.nn.Transformer.html
+++ b/2.9/generated/torch.nn.Transformer.html
@@ -4404,7 +4404,7 @@
 <h1>Transformer<a class="headerlink" href="#transformer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Transformer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Transformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model=512</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_encoder_layers=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_decoder_layers=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_encoder=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_decoder=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Transformer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Transformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model=512</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_encoder_layers=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_decoder_layers=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_encoder=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_decoder=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Transformer" title="Permalink to this definition">#</a></dt>
 <dd><p>A basic transformer layer.</p>
 <p>This Transformer layer implements the original Transformer architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4448,7 +4448,7 @@ <h1>Transformer<a class="headerlink" href="#transformer" title="Permalink to thi
 <a class="github reference external" href="https://github.com/pytorch/examples/tree/master/word_language_model">pytorch/examples</a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Transformer.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Transformer.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Transformer.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Take in and process masked source/target sequences.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4537,7 +4537,7 @@ <h1>Transformer<a class="headerlink" href="#transformer" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Transformer.generate_square_subsequent_mask">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">generate_square_subsequent_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sz</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L292"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Transformer.generate_square_subsequent_mask" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">generate_square_subsequent_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sz</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L292"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Transformer.generate_square_subsequent_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Generate a square causal mask for the sequence.</p>
 <p>The masked positions are filled with float(‘-inf’). Unmasked positions are filled with float(0.0).</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.TransformerDecoder.html b/2.9/generated/torch.nn.TransformerDecoder.html
index 5da7c400ab4..027f3bc2743 100644
--- a/2.9/generated/torch.nn.TransformerDecoder.html
+++ b/2.9/generated/torch.nn.TransformerDecoder.html
@@ -4404,7 +4404,7 @@
 <h1>TransformerDecoder<a class="headerlink" href="#transformerdecoder" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.TransformerDecoder">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TransformerDecoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decoder_layer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerDecoder" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TransformerDecoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decoder_layer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerDecoder" title="Permalink to this definition">#</a></dt>
 <dd><p>TransformerDecoder is a stack of N decoder layers.</p>
 <p>This TransformerDecoder layer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4438,7 +4438,7 @@ <h1>TransformerDecoder<a class="headerlink" href="#transformerdecoder" title="Pe
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.TransformerDecoder.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerDecoder.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerDecoder.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Pass the inputs (and mask) through the decoder layer in turn.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.TransformerDecoderLayer.html b/2.9/generated/torch.nn.TransformerDecoderLayer.html
index 4dd7e481b1e..1ba0778ac50 100644
--- a/2.9/generated/torch.nn.TransformerDecoderLayer.html
+++ b/2.9/generated/torch.nn.TransformerDecoderLayer.html
@@ -4404,7 +4404,7 @@
 <h1>TransformerDecoderLayer<a class="headerlink" href="#transformerdecoderlayer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.TransformerDecoderLayer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TransformerDecoderLayer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L966"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerDecoderLayer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TransformerDecoderLayer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L966"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerDecoderLayer" title="Permalink to this definition">#</a></dt>
 <dd><p>TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network.</p>
 <p>This TransformerDecoderLayer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4454,7 +4454,7 @@ <h1>TransformerDecoderLayer<a class="headerlink" href="#transformerdecoderlayer"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.TransformerDecoderLayer.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerDecoderLayer.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerDecoderLayer.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Pass the inputs (and mask) through the decoder layer.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.TransformerEncoder.html b/2.9/generated/torch.nn.TransformerEncoder.html
index f10d4c5a7a0..4b40f63cebc 100644
--- a/2.9/generated/torch.nn.TransformerEncoder.html
+++ b/2.9/generated/torch.nn.TransformerEncoder.html
@@ -4404,7 +4404,7 @@
 <h1>TransformerEncoder<a class="headerlink" href="#transformerencoder" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.TransformerEncoder">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TransformerEncoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">encoder_layer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_nested_tensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L311"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerEncoder" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TransformerEncoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">encoder_layer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_nested_tensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L311"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerEncoder" title="Permalink to this definition">#</a></dt>
 <dd><p>TransformerEncoder is a stack of N encoder layers.</p>
 <p>This TransformerEncoder layer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4440,7 +4440,7 @@ <h1>TransformerEncoder<a class="headerlink" href="#transformerencoder" title="Pe
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.TransformerEncoder.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerEncoder.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerEncoder.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Pass the input through the encoder layers in turn.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.TransformerEncoderLayer.html b/2.9/generated/torch.nn.TransformerEncoderLayer.html
index 8b121fa9079..35f5a9d4a0e 100644
--- a/2.9/generated/torch.nn.TransformerEncoderLayer.html
+++ b/2.9/generated/torch.nn.TransformerEncoderLayer.html
@@ -4404,7 +4404,7 @@
 <h1>TransformerEncoderLayer<a class="headerlink" href="#transformerencoderlayer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.TransformerEncoderLayer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TransformerEncoderLayer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L645"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerEncoderLayer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TransformerEncoderLayer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L645"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerEncoderLayer" title="Permalink to this definition">#</a></dt>
 <dd><p>TransformerEncoderLayer is made up of self-attn and feedforward network.</p>
 <p>This TransformerEncoderLayer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4484,7 +4484,7 @@ <h1>TransformerEncoderLayer<a class="headerlink" href="#transformerencoderlayer"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.TransformerEncoderLayer.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerEncoderLayer.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TransformerEncoderLayer.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Pass the input through the encoder layer.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.TripletMarginLoss.html b/2.9/generated/torch.nn.TripletMarginLoss.html
index 8515e912bba..d5a2f134c72 100644
--- a/2.9/generated/torch.nn.TripletMarginLoss.html
+++ b/2.9/generated/torch.nn.TripletMarginLoss.html
@@ -4404,7 +4404,7 @@
 <h1>TripletMarginLoss<a class="headerlink" href="#tripletmarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.TripletMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TripletMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1687"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TripletMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TripletMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1687"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TripletMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the triplet loss given an input
 tensors <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>1</mn></mrow><annotation encoding="application/x-tex">x1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">1</span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>2</mn></mrow><annotation encoding="application/x-tex">x2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">2</span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>3</mn></mrow><annotation encoding="application/x-tex">x3</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">3</span></span></span></span></span> and a margin with a value greater than <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mn>0</mn></mrow><annotation encoding="application/x-tex">0</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord">0</span></span></span></span></span>.
 This is used for measuring a relative similarity between samples. A triplet
@@ -4472,7 +4472,7 @@ <h1>TripletMarginLoss<a class="headerlink" href="#tripletmarginloss" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.TripletMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1783"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TripletMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1783"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TripletMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.TripletMarginWithDistanceLoss.html b/2.9/generated/torch.nn.TripletMarginWithDistanceLoss.html
index c022276529b..58678a02d89 100644
--- a/2.9/generated/torch.nn.TripletMarginWithDistanceLoss.html
+++ b/2.9/generated/torch.nn.TripletMarginWithDistanceLoss.html
@@ -4404,7 +4404,7 @@
 <h1>TripletMarginWithDistanceLoss<a class="headerlink" href="#tripletmarginwithdistanceloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.TripletMarginWithDistanceLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TripletMarginWithDistanceLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">distance_function</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1797"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TripletMarginWithDistanceLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">TripletMarginWithDistanceLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">distance_function</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1797"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TripletMarginWithDistanceLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the triplet loss given input
 tensors <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>a</mi></mrow><annotation encoding="application/x-tex">a</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">a</span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>p</mi></mrow><annotation encoding="application/x-tex">p</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal">p</span></span></span></span></span>, and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>n</mi></mrow><annotation encoding="application/x-tex">n</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">n</span></span></span></span></span> (representing anchor,
 positive, and negative examples, respectively), and a nonnegative,
@@ -4505,7 +4505,7 @@ <h1>TripletMarginWithDistanceLoss<a class="headerlink" href="#tripletmarginwithd
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.TripletMarginWithDistanceLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1919"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TripletMarginWithDistanceLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1919"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.TripletMarginWithDistanceLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Unfold.html b/2.9/generated/torch.nn.Unfold.html
index 92ec1202d66..5d697ec2f57 100644
--- a/2.9/generated/torch.nn.Unfold.html
+++ b/2.9/generated/torch.nn.Unfold.html
@@ -4404,7 +4404,7 @@
 <h1>Unfold<a class="headerlink" href="#unfold" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Unfold">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Unfold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Unfold" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Unfold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Unfold" title="Permalink to this definition">#</a></dt>
 <dd><p>Extracts sliding local blocks from a batched input tensor.</p>
 <p>Consider a batched <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mo>∗</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, *)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">∗</span><span class="mclose">)</span></span></span></span></span>,
 where <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>N</mi></mrow><annotation encoding="application/x-tex">N</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span></span></span></span></span> is the batch dimension, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>C</mi></mrow><annotation encoding="application/x-tex">C</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span></span></span></span></span> is the channel dimension,
@@ -4522,7 +4522,7 @@ <h1>Unfold<a class="headerlink" href="#unfold" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Unfold.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L328"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Unfold.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L328"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Unfold.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4533,7 +4533,7 @@ <h1>Unfold<a class="headerlink" href="#unfold" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Unfold.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Unfold.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Unfold.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.Upsample.html b/2.9/generated/torch.nn.Upsample.html
index 6ef6d2cb77e..75349c277e7 100644
--- a/2.9/generated/torch.nn.Upsample.html
+++ b/2.9/generated/torch.nn.Upsample.html
@@ -4404,7 +4404,7 @@
 <h1>Upsample<a class="headerlink" href="#upsample" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.Upsample">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Upsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompute_scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Upsample" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">Upsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompute_scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Upsample" title="Permalink to this definition">#</a></dt>
 <dd><p>Upsamples a given multi-channel 1D (temporal), 2D (spatial) or 3D (volumetric) data.</p>
 <p>The input data is assumed to be of the form
 <cite>minibatch x channels x [optional depth] x [optional height] x width</cite>.
@@ -4529,7 +4529,7 @@ <h1>Upsample<a class="headerlink" href="#upsample" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Upsample.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Upsample.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Upsample.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4540,7 +4540,7 @@ <h1>Upsample<a class="headerlink" href="#upsample" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.Upsample.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Upsample.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.Upsample.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.UpsamplingBilinear2d.html b/2.9/generated/torch.nn.UpsamplingBilinear2d.html
index b51102bebbe..b2c87a06597 100644
--- a/2.9/generated/torch.nn.UpsamplingBilinear2d.html
+++ b/2.9/generated/torch.nn.UpsamplingBilinear2d.html
@@ -4404,7 +4404,7 @@
 <h1>UpsamplingBilinear2d<a class="headerlink" href="#upsamplingbilinear2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.UpsamplingBilinear2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">UpsamplingBilinear2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.UpsamplingBilinear2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">UpsamplingBilinear2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.UpsamplingBilinear2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D bilinear upsampling to an input signal composed of several input channels.</p>
 <p>To specify the scale, it takes either the <code class="xref py py-attr docutils literal notranslate"><span class="pre">size</span></code> or the <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale_factor</span></code>
 as it’s constructor argument.</p>
diff --git a/2.9/generated/torch.nn.UpsamplingNearest2d.html b/2.9/generated/torch.nn.UpsamplingNearest2d.html
index 8840ac12c60..50709bd83ea 100644
--- a/2.9/generated/torch.nn.UpsamplingNearest2d.html
+++ b/2.9/generated/torch.nn.UpsamplingNearest2d.html
@@ -4404,7 +4404,7 @@
 <h1>UpsamplingNearest2d<a class="headerlink" href="#upsamplingnearest2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.UpsamplingNearest2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">UpsamplingNearest2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L202"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.UpsamplingNearest2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">UpsamplingNearest2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L202"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.UpsamplingNearest2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D nearest neighbor upsampling to an input signal composed of several input channels.</p>
 <p>To specify the scale, it takes either the <code class="xref py py-attr docutils literal notranslate"><span class="pre">size</span></code> or the <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale_factor</span></code>
 as it’s constructor argument.</p>
diff --git a/2.9/generated/torch.nn.ZeroPad1d.html b/2.9/generated/torch.nn.ZeroPad1d.html
index 7eab91eede6..3d59709c883 100644
--- a/2.9/generated/torch.nn.ZeroPad1d.html
+++ b/2.9/generated/torch.nn.ZeroPad1d.html
@@ -4404,7 +4404,7 @@
 <h1>ZeroPad1d<a class="headerlink" href="#zeropad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ZeroPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ZeroPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ZeroPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with zero.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4451,7 +4451,7 @@ <h1>ZeroPad1d<a class="headerlink" href="#zeropad1d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ZeroPad1d.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad1d.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad1d.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ZeroPad2d.html b/2.9/generated/torch.nn.ZeroPad2d.html
index eca3bb28e3e..478819cef9c 100644
--- a/2.9/generated/torch.nn.ZeroPad2d.html
+++ b/2.9/generated/torch.nn.ZeroPad2d.html
@@ -4404,7 +4404,7 @@
 <h1>ZeroPad2d<a class="headerlink" href="#zeropad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ZeroPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ZeroPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L731"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ZeroPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L731"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with zero.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4451,7 +4451,7 @@ <h1>ZeroPad2d<a class="headerlink" href="#zeropad2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ZeroPad2d.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad2d.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad2d.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.ZeroPad3d.html b/2.9/generated/torch.nn.ZeroPad3d.html
index 37356ebfc85..7b26b988048 100644
--- a/2.9/generated/torch.nn.ZeroPad3d.html
+++ b/2.9/generated/torch.nn.ZeroPad3d.html
@@ -4404,7 +4404,7 @@
 <h1>ZeroPad3d<a class="headerlink" href="#zeropad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.ZeroPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ZeroPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L788"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">ZeroPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L788"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with zero.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4439,7 +4439,7 @@ <h1>ZeroPad3d<a class="headerlink" href="#zeropad3d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.ZeroPad3d.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L826"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad3d.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L826"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.ZeroPad3d.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.attention.bias.CausalBias.html b/2.9/generated/torch.nn.attention.bias.CausalBias.html
index feae9e68032..8ee8d0f0476 100644
--- a/2.9/generated/torch.nn.attention.bias.CausalBias.html
+++ b/2.9/generated/torch.nn.attention.bias.CausalBias.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.attention.bias.CausalBias<a class="headerlink" href="#torch-nn-attention-bias-causalbias" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.attention.bias.CausalBias">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.bias.</span></span><span class="sig-name descname"><span class="pre">CausalBias</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">variant</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seq_len_q</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seq_len_kv</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/bias.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.bias.CausalBias" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.bias.</span></span><span class="sig-name descname"><span class="pre">CausalBias</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">variant</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seq_len_q</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seq_len_kv</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/bias.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.bias.CausalBias" title="Permalink to this definition">#</a></dt>
 <dd><p>A bias representing causal attention patterns. For an overview of the bias structure, see the <a class="reference internal" href="torch.nn.attention.bias.CausalVariant.html#torch.nn.attention.bias.CausalVariant" title="torch.nn.attention.bias.CausalVariant"><code class="xref py py-class docutils literal notranslate"><span class="pre">CausalVariant</span></code></a> enum.</p>
 <p>This class is used for defining causal (triangular) attention biases. For construing the bias, there exist
 two factory functions: <a class="reference internal" href="torch.nn.attention.bias.causal_upper_left.html#torch.nn.attention.bias.causal_upper_left" title="torch.nn.attention.bias.causal_upper_left"><code class="xref py py-func docutils literal notranslate"><span class="pre">causal_upper_left()</span></code></a> and <a class="reference internal" href="torch.nn.attention.bias.causal_lower_right.html#torch.nn.attention.bias.causal_lower_right" title="torch.nn.attention.bias.causal_lower_right"><code class="xref py py-func docutils literal notranslate"><span class="pre">causal_lower_right()</span></code></a>.</p>
diff --git a/2.9/generated/torch.nn.attention.bias.CausalVariant.html b/2.9/generated/torch.nn.attention.bias.CausalVariant.html
index 1f1ff61c8b0..a02d8cc56b9 100644
--- a/2.9/generated/torch.nn.attention.bias.CausalVariant.html
+++ b/2.9/generated/torch.nn.attention.bias.CausalVariant.html
@@ -4415,7 +4415,7 @@
 <h1>CausalVariant<a class="headerlink" href="#causalvariant" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.attention.bias.CausalVariant">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.bias.</span></span><span class="sig-name descname"><span class="pre">CausalVariant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/bias.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.bias.CausalVariant" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.bias.</span></span><span class="sig-name descname"><span class="pre">CausalVariant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/bias.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.bias.CausalVariant" title="Permalink to this definition">#</a></dt>
 <dd><p>Enum for causal variants used in attention mechanisms.</p>
 <p>Defines two types of causal biases:</p>
 <p><code class="docutils literal notranslate"><span class="pre">UPPER_LEFT</span></code>: Represents upper-left triangular bias for standard causal attention.
diff --git a/2.9/generated/torch.nn.attention.bias.causal_lower_right.html b/2.9/generated/torch.nn.attention.bias.causal_lower_right.html
index ef521c986d9..2b964ef6b45 100644
--- a/2.9/generated/torch.nn.attention.bias.causal_lower_right.html
+++ b/2.9/generated/torch.nn.attention.bias.causal_lower_right.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.attention.bias.causal_lower_right<a class="headerlink" href="#torch-nn-attention-bias-causal-lower-right" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.bias.causal_lower_right">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.bias.</span></span><span class="sig-name descname"><span class="pre">causal_lower_right</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/bias.py#L334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.bias.causal_lower_right" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.bias.</span></span><span class="sig-name descname"><span class="pre">causal_lower_right</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/bias.py#L334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.bias.causal_lower_right" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a lower-right triangular causal bias.</p>
 <p>This function generates a lower-right triangular matrix to represent causal attention bias with a
 diagonal offset set so that the inclusive values are aligned to the lower right corner of the matrix.</p>
diff --git a/2.9/generated/torch.nn.attention.bias.causal_upper_left.html b/2.9/generated/torch.nn.attention.bias.causal_upper_left.html
index 71329d09299..1a664c6bf14 100644
--- a/2.9/generated/torch.nn.attention.bias.causal_upper_left.html
+++ b/2.9/generated/torch.nn.attention.bias.causal_upper_left.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.attention.bias.causal_upper_left<a class="headerlink" href="#torch-nn-attention-bias-causal-upper-left" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.bias.causal_upper_left">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.bias.</span></span><span class="sig-name descname"><span class="pre">causal_upper_left</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/bias.py#L301"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.bias.causal_upper_left" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.bias.</span></span><span class="sig-name descname"><span class="pre">causal_upper_left</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/bias.py#L301"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.bias.causal_upper_left" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates an upper-left triangular causal bias.</p>
 <p>This function generates a upper-left triangular matrix to represent causal attention bias with a
 diagonal offset set so that the inclusive values are aligned to the upper left corner of the matrix.
diff --git a/2.9/generated/torch.nn.attention.sdpa_kernel.html b/2.9/generated/torch.nn.attention.sdpa_kernel.html
index 5230def9334..74625ed3262 100644
--- a/2.9/generated/torch.nn.attention.sdpa_kernel.html
+++ b/2.9/generated/torch.nn.attention.sdpa_kernel.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.attention.sdpa_kernel<a class="headerlink" href="#torch-nn-attention-sdpa-kernel" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.sdpa_kernel">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.</span></span><span class="sig-name descname"><span class="pre">sdpa_kernel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backends</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">set_priority</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/__init__.py#L106"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.sdpa_kernel" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.</span></span><span class="sig-name descname"><span class="pre">sdpa_kernel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backends</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">set_priority</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/__init__.py#L106"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.sdpa_kernel" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager to select which backend to use for scaled dot product attention.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.factory_kwargs.html b/2.9/generated/torch.nn.factory_kwargs.html
index 4401cc77e37..99b0a861578 100644
--- a/2.9/generated/torch.nn.factory_kwargs.html
+++ b/2.9/generated/torch.nn.factory_kwargs.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.factory_kwargs<a class="headerlink" href="#torch-nn-factory-kwargs" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.factory_kwargs">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">factory_kwargs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/__init__.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.factory_kwargs" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.</span></span><span class="sig-name descname"><span class="pre">factory_kwargs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/__init__.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.factory_kwargs" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a canonicalized dict of factory kwargs.</p>
 <p>Given kwargs, returns a canonicalized dict of factory kwargs that can be directly passed
 to factory functions like torch.empty, or errors if unrecognized kwargs are present.</p>
diff --git a/2.9/generated/torch.nn.functional.adaptive_avg_pool2d.html b/2.9/generated/torch.nn.functional.adaptive_avg_pool2d.html
index 3747293f668..d24294f59cf 100644
--- a/2.9/generated/torch.nn.functional.adaptive_avg_pool2d.html
+++ b/2.9/generated/torch.nn.functional.adaptive_avg_pool2d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.adaptive_avg_pool2d<a class="headerlink" href="#torch-nn-functional-adaptive-avg-pool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.adaptive_avg_pool2d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_avg_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1363"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_avg_pool2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_avg_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1363"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_avg_pool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a 2D adaptive average pooling over an input signal composed of several input planes.</p>
 <p>See <a class="reference internal" href="torch.nn.AdaptiveAvgPool2d.html#torch.nn.AdaptiveAvgPool2d" title="torch.nn.AdaptiveAvgPool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">AdaptiveAvgPool2d</span></code></a> for details and output shape.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.adaptive_avg_pool3d.html b/2.9/generated/torch.nn.functional.adaptive_avg_pool3d.html
index 6f4aeabfde8..ff191f5409a 100644
--- a/2.9/generated/torch.nn.functional.adaptive_avg_pool3d.html
+++ b/2.9/generated/torch.nn.functional.adaptive_avg_pool3d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.adaptive_avg_pool3d<a class="headerlink" href="#torch-nn-functional-adaptive-avg-pool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.adaptive_avg_pool3d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_avg_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1378"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_avg_pool3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_avg_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1378"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_avg_pool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a 3D adaptive average pooling over an input signal composed of several input planes.</p>
 <p>See <a class="reference internal" href="torch.nn.AdaptiveAvgPool3d.html#torch.nn.AdaptiveAvgPool3d" title="torch.nn.AdaptiveAvgPool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">AdaptiveAvgPool3d</span></code></a> for details and output shape.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.adaptive_max_pool1d.html b/2.9/generated/torch.nn.functional.adaptive_max_pool1d.html
index 9cad6ad8f25..f5de05575a7 100644
--- a/2.9/generated/torch.nn.functional.adaptive_max_pool1d.html
+++ b/2.9/generated/torch.nn.functional.adaptive_max_pool1d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.adaptive_max_pool1d<a class="headerlink" href="#torch-nn-functional-adaptive-max-pool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.adaptive_max_pool1d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_max_pool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_max_pool1d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_max_pool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_max_pool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D adaptive max pooling over an input signal composed of
 several input planes.</p>
 <p>See <a class="reference internal" href="torch.nn.AdaptiveMaxPool1d.html#torch.nn.AdaptiveMaxPool1d" title="torch.nn.AdaptiveMaxPool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">AdaptiveMaxPool1d</span></code></a> for details and output shape.</p>
diff --git a/2.9/generated/torch.nn.functional.adaptive_max_pool2d.html b/2.9/generated/torch.nn.functional.adaptive_max_pool2d.html
index b6214326548..1eb4e49c0af 100644
--- a/2.9/generated/torch.nn.functional.adaptive_max_pool2d.html
+++ b/2.9/generated/torch.nn.functional.adaptive_max_pool2d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.adaptive_max_pool2d<a class="headerlink" href="#torch-nn-functional-adaptive-max-pool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.adaptive_max_pool2d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_max_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_max_pool2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_max_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_max_pool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D adaptive max pooling over an input signal composed of
 several input planes.</p>
 <p>See <a class="reference internal" href="torch.nn.AdaptiveMaxPool2d.html#torch.nn.AdaptiveMaxPool2d" title="torch.nn.AdaptiveMaxPool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">AdaptiveMaxPool2d</span></code></a> for details and output shape.</p>
diff --git a/2.9/generated/torch.nn.functional.adaptive_max_pool3d.html b/2.9/generated/torch.nn.functional.adaptive_max_pool3d.html
index 9205d7e45f0..3f769e4a2a9 100644
--- a/2.9/generated/torch.nn.functional.adaptive_max_pool3d.html
+++ b/2.9/generated/torch.nn.functional.adaptive_max_pool3d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.adaptive_max_pool3d<a class="headerlink" href="#torch-nn-functional-adaptive-max-pool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.adaptive_max_pool3d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_max_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_max_pool3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">adaptive_max_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.adaptive_max_pool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D adaptive max pooling over an input signal composed of
 several input planes.</p>
 <p>See <a class="reference internal" href="torch.nn.AdaptiveMaxPool3d.html#torch.nn.AdaptiveMaxPool3d" title="torch.nn.AdaptiveMaxPool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">AdaptiveMaxPool3d</span></code></a> for details and output shape.</p>
diff --git a/2.9/generated/torch.nn.functional.affine_grid.html b/2.9/generated/torch.nn.functional.affine_grid.html
index 66dc8a765ed..24c0e3ed7a1 100644
--- a/2.9/generated/torch.nn.functional.affine_grid.html
+++ b/2.9/generated/torch.nn.functional.affine_grid.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.affine_grid<a class="headerlink" href="#torch-nn-functional-affine-grid" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.affine_grid">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">affine_grid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">theta</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L5111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.affine_grid" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">affine_grid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">theta</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L5111"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.affine_grid" title="Permalink to this definition">#</a></dt>
 <dd><p>Generate 2D or 3D flow field (sampling grid), given a batch of affine matrices <code class="xref py py-attr docutils literal notranslate"><span class="pre">theta</span></code>.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.nn.functional.alpha_dropout.html b/2.9/generated/torch.nn.functional.alpha_dropout.html
index 148760daf18..025e22597a4 100644
--- a/2.9/generated/torch.nn.functional.alpha_dropout.html
+++ b/2.9/generated/torch.nn.functional.alpha_dropout.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.alpha_dropout<a class="headerlink" href="#torch-nn-functional-alpha-dropout" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.alpha_dropout">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">alpha_dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.alpha_dropout" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">alpha_dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.alpha_dropout" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply alpha dropout to the input.</p>
 <p>See <a class="reference internal" href="torch.nn.AlphaDropout.html#torch.nn.AlphaDropout" title="torch.nn.AlphaDropout"><code class="xref py py-class docutils literal notranslate"><span class="pre">AlphaDropout</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.batch_norm.html b/2.9/generated/torch.nn.functional.batch_norm.html
index 60083c8d229..f3e26b52eaf 100644
--- a/2.9/generated/torch.nn.functional.batch_norm.html
+++ b/2.9/generated/torch.nn.functional.batch_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.batch_norm<a class="headerlink" href="#torch-nn-functional-batch-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.batch_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">batch_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">running_mean</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">running_var</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2782"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.batch_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">batch_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">running_mean</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">running_var</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2782"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.batch_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply Batch Normalization for each channel across a batch of data.</p>
 <p>See <a class="reference internal" href="torch.nn.BatchNorm1d.html#torch.nn.BatchNorm1d" title="torch.nn.BatchNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm1d</span></code></a>, <a class="reference internal" href="torch.nn.BatchNorm2d.html#torch.nn.BatchNorm2d" title="torch.nn.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm2d</span></code></a>,
 <a class="reference internal" href="torch.nn.BatchNorm3d.html#torch.nn.BatchNorm3d" title="torch.nn.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm3d</span></code></a> for details.</p>
diff --git a/2.9/generated/torch.nn.functional.binary_cross_entropy.html b/2.9/generated/torch.nn.functional.binary_cross_entropy.html
index 790ca201db5..5e196e38ed4 100644
--- a/2.9/generated/torch.nn.functional.binary_cross_entropy.html
+++ b/2.9/generated/torch.nn.functional.binary_cross_entropy.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.binary_cross_entropy<a class="headerlink" href="#torch-nn-functional-binary-cross-entropy" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.binary_cross_entropy">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">binary_cross_entropy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3468"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.binary_cross_entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">binary_cross_entropy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3468"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.binary_cross_entropy" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute Binary Cross Entropy between the target and input probabilities.</p>
 <p>See <a class="reference internal" href="torch.nn.BCELoss.html#torch.nn.BCELoss" title="torch.nn.BCELoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">BCELoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.binary_cross_entropy_with_logits.html b/2.9/generated/torch.nn.functional.binary_cross_entropy_with_logits.html
index 87036e1cee4..95e53658a13 100644
--- a/2.9/generated/torch.nn.functional.binary_cross_entropy_with_logits.html
+++ b/2.9/generated/torch.nn.functional.binary_cross_entropy_with_logits.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.binary_cross_entropy_with_logits<a class="headerlink" href="#torch-nn-functional-binary-cross-entropy-with-logits" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.binary_cross_entropy_with_logits">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">binary_cross_entropy_with_logits</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3529"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.binary_cross_entropy_with_logits" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">binary_cross_entropy_with_logits</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3529"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.binary_cross_entropy_with_logits" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute Binary Cross Entropy between target and input logits.</p>
 <p>See <a class="reference internal" href="torch.nn.BCEWithLogitsLoss.html#torch.nn.BCEWithLogitsLoss" title="torch.nn.BCEWithLogitsLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">BCEWithLogitsLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.celu.html b/2.9/generated/torch.nn.functional.celu.html
index 96090b68297..04bc6870ca0 100644
--- a/2.9/generated/torch.nn.functional.celu.html
+++ b/2.9/generated/torch.nn.functional.celu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.celu<a class="headerlink" href="#torch-nn-functional-celu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.celu">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">celu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1842"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.celu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">celu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1842"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.celu" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies element-wise,
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>CELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>α</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mi mathvariant="normal">/</mi><mi>α</mi><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{CELU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1))</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">CELU</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">min</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.0037em;">α</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">∗</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mop">exp</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mord">/</span><span class="mord mathnormal" style="margin-right:0.0037em;">α</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">−</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord">1</span><span class="mclose">))</span></span></span></span></span>.</p>
 <p>See <a class="reference internal" href="torch.nn.CELU.html#torch.nn.CELU" title="torch.nn.CELU"><code class="xref py py-class docutils literal notranslate"><span class="pre">CELU</span></code></a> for more details.</p>
diff --git a/2.9/generated/torch.nn.functional.cosine_embedding_loss.html b/2.9/generated/torch.nn.functional.cosine_embedding_loss.html
index ea8a3648ec8..08cdf3d6232 100644
--- a/2.9/generated/torch.nn.functional.cosine_embedding_loss.html
+++ b/2.9/generated/torch.nn.functional.cosine_embedding_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.cosine_embedding_loss<a class="headerlink" href="#torch-nn-functional-cosine-embedding-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.cosine_embedding_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">cosine_embedding_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.cosine_embedding_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">cosine_embedding_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.cosine_embedding_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the cosine embedding loss.</p>
 <p>See <a class="reference internal" href="torch.nn.CosineEmbeddingLoss.html#torch.nn.CosineEmbeddingLoss" title="torch.nn.CosineEmbeddingLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">CosineEmbeddingLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.cross_entropy.html b/2.9/generated/torch.nn.functional.cross_entropy.html
index 94cd7cea1c4..b3189c43ccb 100644
--- a/2.9/generated/torch.nn.functional.cross_entropy.html
+++ b/2.9/generated/torch.nn.functional.cross_entropy.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.cross_entropy<a class="headerlink" href="#torch-nn-functional-cross-entropy" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.cross_entropy">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">cross_entropy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label_smoothing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3375"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.cross_entropy" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">cross_entropy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label_smoothing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3375"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.cross_entropy" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the cross entropy loss between input logits and target.</p>
 <p>See <a class="reference internal" href="torch.nn.CrossEntropyLoss.html#torch.nn.CrossEntropyLoss" title="torch.nn.CrossEntropyLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">CrossEntropyLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.ctc_loss.html b/2.9/generated/torch.nn.functional.ctc_loss.html
index c2109de1e55..5b73d49e837 100644
--- a/2.9/generated/torch.nn.functional.ctc_loss.html
+++ b/2.9/generated/torch.nn.functional.ctc_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.ctc_loss<a class="headerlink" href="#torch-nn-functional-ctc-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.ctc_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">ctc_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_probs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">targets</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">blank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_infinity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3006"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.ctc_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">ctc_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_probs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">targets</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">blank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_infinity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3006"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.ctc_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the Connectionist Temporal Classification loss.</p>
 <p>See <a class="reference internal" href="torch.nn.CTCLoss.html#torch.nn.CTCLoss" title="torch.nn.CTCLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">CTCLoss</span></code></a> for details.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.nn.functional.dropout.html b/2.9/generated/torch.nn.functional.dropout.html
index 5561b0b64f6..d519808f6b2 100644
--- a/2.9/generated/torch.nn.functional.dropout.html
+++ b/2.9/generated/torch.nn.functional.dropout.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.dropout<a class="headerlink" href="#torch-nn-functional-dropout" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.dropout">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1394"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.dropout" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1394"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.dropout" title="Permalink to this definition">#</a></dt>
 <dd><p>During training, randomly zeroes some elements of the input tensor with probability <code class="xref py py-attr docutils literal notranslate"><span class="pre">p</span></code>.</p>
 <p>Uses samples from a Bernoulli distribution.</p>
 <p>See <a class="reference internal" href="torch.nn.Dropout.html#torch.nn.Dropout" title="torch.nn.Dropout"><code class="xref py py-class docutils literal notranslate"><span class="pre">Dropout</span></code></a> for details.</p>
diff --git a/2.9/generated/torch.nn.functional.dropout1d.html b/2.9/generated/torch.nn.functional.dropout1d.html
index 470a0251b59..559ef8e381e 100644
--- a/2.9/generated/torch.nn.functional.dropout1d.html
+++ b/2.9/generated/torch.nn.functional.dropout1d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.dropout1d<a class="headerlink" href="#torch-nn-functional-dropout1d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.dropout1d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">dropout1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1445"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.dropout1d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">dropout1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1445"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.dropout1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels (a channel is a 1D feature map).</p>
 <p>For example, the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
 batched input is a 1D tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>input</mtext><mo stretchy="false">[</mo><mi>i</mi><mo separator="true">,</mo><mi>j</mi><mo stretchy="false">]</mo></mrow><annotation encoding="application/x-tex">\text{input}[i, j]</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">input</span></span><span class="mopen">[</span><span class="mord mathnormal">i</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span><span class="mclose">]</span></span></span></span></span> of the input tensor.
diff --git a/2.9/generated/torch.nn.functional.dropout2d.html b/2.9/generated/torch.nn.functional.dropout2d.html
index d8e9227f0d3..c57ae40d4f7 100644
--- a/2.9/generated/torch.nn.functional.dropout2d.html
+++ b/2.9/generated/torch.nn.functional.dropout2d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.dropout2d<a class="headerlink" href="#torch-nn-functional-dropout2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.dropout2d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">dropout2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1496"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.dropout2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">dropout2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1496"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.dropout2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels (a channel is a 2D feature map).</p>
 <p>For example, the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
 batched input is a 2D tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>input</mtext><mo stretchy="false">[</mo><mi>i</mi><mo separator="true">,</mo><mi>j</mi><mo stretchy="false">]</mo></mrow><annotation encoding="application/x-tex">\text{input}[i, j]</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">input</span></span><span class="mopen">[</span><span class="mord mathnormal">i</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span><span class="mclose">]</span></span></span></span></span> of the input tensor.
diff --git a/2.9/generated/torch.nn.functional.dropout3d.html b/2.9/generated/torch.nn.functional.dropout3d.html
index 7910bcb1f78..72370a86129 100644
--- a/2.9/generated/torch.nn.functional.dropout3d.html
+++ b/2.9/generated/torch.nn.functional.dropout3d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.dropout3d<a class="headerlink" href="#torch-nn-functional-dropout3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.dropout3d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">dropout3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1555"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.dropout3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">dropout3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1555"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.dropout3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels (a channel is a 3D feature map).</p>
 <p>For example, the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
 batched input is a 3D tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>input</mtext><mo stretchy="false">[</mo><mi>i</mi><mo separator="true">,</mo><mi>j</mi><mo stretchy="false">]</mo></mrow><annotation encoding="application/x-tex">\text{input}[i, j]</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">input</span></span><span class="mopen">[</span><span class="mord mathnormal">i</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span><span class="mclose">]</span></span></span></span></span> of the input tensor.
diff --git a/2.9/generated/torch.nn.functional.elu.html b/2.9/generated/torch.nn.functional.elu.html
index a5d16a61317..4ed2ebc1ddc 100644
--- a/2.9/generated/torch.nn.functional.elu.html
+++ b/2.9/generated/torch.nn.functional.elu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.elu<a class="headerlink" href="#torch-nn-functional-elu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.elu">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">elu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1789"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.elu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">elu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1789"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.elu" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply the Exponential Linear Unit (ELU) function element-wise.</p>
 <p>See <a class="reference internal" href="torch.nn.ELU.html#torch.nn.ELU" title="torch.nn.ELU"><code class="xref py py-class docutils literal notranslate"><span class="pre">ELU</span></code></a> for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.embedding.html b/2.9/generated/torch.nn.functional.embedding.html
index ece8c0e1fde..991b9865a89 100644
--- a/2.9/generated/torch.nn.functional.embedding.html
+++ b/2.9/generated/torch.nn.functional.embedding.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.embedding<a class="headerlink" href="#torch-nn-functional-embedding" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.embedding">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2428"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.embedding" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2428"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.embedding" title="Permalink to this definition">#</a></dt>
 <dd><p>Generate a simple lookup table that looks up embeddings in a fixed dictionary and size.</p>
 <p>This module is often used to retrieve word embeddings using indices.
 The input to the module is a list of indices, and the embedding matrix,
diff --git a/2.9/generated/torch.nn.functional.embedding_bag.html b/2.9/generated/torch.nn.functional.embedding_bag.html
index 0e707db32a6..b0df51ce1ef 100644
--- a/2.9/generated/torch.nn.functional.embedding_bag.html
+++ b/2.9/generated/torch.nn.functional.embedding_bag.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.embedding_bag<a class="headerlink" href="#torch-nn-functional-embedding-bag" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.embedding_bag">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">embedding_bag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offsets</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">per_sample_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2545"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.embedding_bag" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">embedding_bag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offsets</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">per_sample_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2545"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.embedding_bag" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute sums, means or maxes of <cite>bags</cite> of embeddings.</p>
 <p>Calculation is done without instantiating the intermediate embeddings.
 See <a class="reference internal" href="torch.nn.EmbeddingBag.html#torch.nn.EmbeddingBag" title="torch.nn.EmbeddingBag"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.EmbeddingBag</span></code></a> for more details.</p>
diff --git a/2.9/generated/torch.nn.functional.feature_alpha_dropout.html b/2.9/generated/torch.nn.functional.feature_alpha_dropout.html
index 41ec90a38b0..304e26d6adc 100644
--- a/2.9/generated/torch.nn.functional.feature_alpha_dropout.html
+++ b/2.9/generated/torch.nn.functional.feature_alpha_dropout.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.feature_alpha_dropout<a class="headerlink" href="#torch-nn-functional-feature-alpha-dropout" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.feature_alpha_dropout">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">feature_alpha_dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1607"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.feature_alpha_dropout" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">feature_alpha_dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1607"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.feature_alpha_dropout" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly masks out entire channels (a channel is a feature map).</p>
 <p>For example, the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the batch input
 is a tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>input</mtext><mo stretchy="false">[</mo><mi>i</mi><mo separator="true">,</mo><mi>j</mi><mo stretchy="false">]</mo></mrow><annotation encoding="application/x-tex">\text{input}[i, j]</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">input</span></span><span class="mopen">[</span><span class="mord mathnormal">i</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span><span class="mclose">]</span></span></span></span></span> of the input tensor. Instead of
diff --git a/2.9/generated/torch.nn.functional.fold.html b/2.9/generated/torch.nn.functional.fold.html
index 8c84d71fdd4..35fd1d7c294 100644
--- a/2.9/generated/torch.nn.functional.fold.html
+++ b/2.9/generated/torch.nn.functional.fold.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.fold<a class="headerlink" href="#torch-nn-functional-fold" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.fold">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">fold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L5620"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.fold" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">fold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L5620"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.fold" title="Permalink to this definition">#</a></dt>
 <dd><p>Combine an array of sliding local blocks into a large containing tensor.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.functional.fractional_max_pool2d.html b/2.9/generated/torch.nn.functional.fractional_max_pool2d.html
index 42c56156b7f..fe2de2627ea 100644
--- a/2.9/generated/torch.nn.functional.fractional_max_pool2d.html
+++ b/2.9/generated/torch.nn.functional.fractional_max_pool2d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.fractional_max_pool2d<a class="headerlink" href="#torch-nn-functional-fractional-max-pool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.fractional_max_pool2d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">fractional_max_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.fractional_max_pool2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">fractional_max_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.fractional_max_pool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies 2D fractional max pooling over an input signal composed of several input planes.</p>
 <p>Fractional MaxPooling is described in detail in the paper <a class="reference external" href="http://arxiv.org/abs/1412.6071">Fractional MaxPooling</a> by Ben Graham</p>
 <p>The max-pooling operation is applied in <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi><mi>H</mi><mo>×</mo><mi>k</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">kH \times kW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span></span></span></span></span> regions by a stochastic
diff --git a/2.9/generated/torch.nn.functional.fractional_max_pool3d.html b/2.9/generated/torch.nn.functional.fractional_max_pool3d.html
index 1c5f886a6ec..4b239699c80 100644
--- a/2.9/generated/torch.nn.functional.fractional_max_pool3d.html
+++ b/2.9/generated/torch.nn.functional.fractional_max_pool3d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.fractional_max_pool3d<a class="headerlink" href="#torch-nn-functional-fractional-max-pool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.fractional_max_pool3d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">fractional_max_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.fractional_max_pool3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">fractional_max_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.fractional_max_pool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies 3D fractional max pooling over an input signal composed of several input planes.</p>
 <p>Fractional MaxPooling is described in detail in the paper <a class="reference external" href="http://arxiv.org/abs/1412.6071">Fractional MaxPooling</a> by Ben Graham</p>
 <p>The max-pooling operation is applied in <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi><mi>T</mi><mo>×</mo><mi>k</mi><mi>H</mi><mo>×</mo><mi>k</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">kT \times kH \times kW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.13889em;">T</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span></span></span></span></span> regions by a stochastic
diff --git a/2.9/generated/torch.nn.functional.gaussian_nll_loss.html b/2.9/generated/torch.nn.functional.gaussian_nll_loss.html
index f46d9e860f6..2aa7ef72099 100644
--- a/2.9/generated/torch.nn.functional.gaussian_nll_loss.html
+++ b/2.9/generated/torch.nn.functional.gaussian_nll_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.gaussian_nll_loss<a class="headerlink" href="#torch-nn-functional-gaussian-nll-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.gaussian_nll_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">gaussian_nll_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">var</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3208"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.gaussian_nll_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">gaussian_nll_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">var</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3208"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.gaussian_nll_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the Gaussian negative log likelihood loss.</p>
 <p>See <a class="reference internal" href="torch.nn.GaussianNLLLoss.html#torch.nn.GaussianNLLLoss" title="torch.nn.GaussianNLLLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">GaussianNLLLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.glu.html b/2.9/generated/torch.nn.functional.glu.html
index f27ba848597..941ad8ec44d 100644
--- a/2.9/generated/torch.nn.functional.glu.html
+++ b/2.9/generated/torch.nn.functional.glu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.glu<a class="headerlink" href="#torch-nn-functional-glu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.glu">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">glu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1711"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.glu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">glu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1711"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.glu" title="Permalink to this definition">#</a></dt>
 <dd><p>The gated linear unit. Computes:</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>GLU</mtext><mo stretchy="false">(</mo><mi>a</mi><mo separator="true">,</mo><mi>b</mi><mo stretchy="false">)</mo><mo>=</mo><mi>a</mi><mo>⊗</mo><mi>σ</mi><mo stretchy="false">(</mo><mi>b</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{GLU}(a, b) = a \otimes \sigma(b)
diff --git a/2.9/generated/torch.nn.functional.grid_sample.html b/2.9/generated/torch.nn.functional.grid_sample.html
index 08fd12e5f09..a9d763fde8d 100644
--- a/2.9/generated/torch.nn.functional.grid_sample.html
+++ b/2.9/generated/torch.nn.functional.grid_sample.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.grid_sample<a class="headerlink" href="#torch-nn-functional-grid-sample" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.grid_sample">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">grid_sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grid</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'bilinear'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4952"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.grid_sample" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">grid_sample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grid</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'bilinear'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4952"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.grid_sample" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute grid sample.</p>
 <p>Given an <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> and a flow-field <code class="xref py py-attr docutils literal notranslate"><span class="pre">grid</span></code>, computes the
 <code class="docutils literal notranslate"><span class="pre">output</span></code> using <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> values and pixel locations from <code class="xref py py-attr docutils literal notranslate"><span class="pre">grid</span></code>.</p>
diff --git a/2.9/generated/torch.nn.functional.group_norm.html b/2.9/generated/torch.nn.functional.group_norm.html
index d52f47ee4a9..b7847129623 100644
--- a/2.9/generated/torch.nn.functional.group_norm.html
+++ b/2.9/generated/torch.nn.functional.group_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.group_norm<a class="headerlink" href="#torch-nn-functional-group-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.group_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">group_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_groups</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2923"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.group_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">group_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_groups</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2923"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.group_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply Group Normalization for last certain number of dimensions.</p>
 <p>See <a class="reference internal" href="torch.nn.GroupNorm.html#torch.nn.GroupNorm" title="torch.nn.GroupNorm"><code class="xref py py-class docutils literal notranslate"><span class="pre">GroupNorm</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.gumbel_softmax.html b/2.9/generated/torch.nn.functional.gumbel_softmax.html
index 20566939d7a..7eeba290916 100644
--- a/2.9/generated/torch.nn.functional.gumbel_softmax.html
+++ b/2.9/generated/torch.nn.functional.gumbel_softmax.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.gumbel_softmax<a class="headerlink" href="#torch-nn-functional-gumbel-softmax" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.gumbel_softmax">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">gumbel_softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">logits</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tau</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hard</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.gumbel_softmax" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">gumbel_softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">logits</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tau</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hard</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.gumbel_softmax" title="Permalink to this definition">#</a></dt>
 <dd><p>Sample from the Gumbel-Softmax distribution (<a class="reference external" href="https://arxiv.org/abs/1611.00712">Link 1</a>  <a class="reference external" href="https://arxiv.org/abs/1611.01144">Link 2</a>) and optionally discretize.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.functional.hardsigmoid.html b/2.9/generated/torch.nn.functional.hardsigmoid.html
index dd7c8d143d7..384c56a5cf7 100644
--- a/2.9/generated/torch.nn.functional.hardsigmoid.html
+++ b/2.9/generated/torch.nn.functional.hardsigmoid.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.hardsigmoid<a class="headerlink" href="#torch-nn-functional-hardsigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.hardsigmoid">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">hardsigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2280"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.hardsigmoid" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">hardsigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2280"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.hardsigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply the Hardsigmoid function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>Hardsigmoid</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mrow><mo fence="true">{</mo><mtable rowspacing="0.36em" columnalign="left left" columnspacing="1em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mn>0</mn></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mtext>if </mtext><mi>x</mi><mo>≤</mo><mo>−</mo><mn>3</mn><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mn>1</mn></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mtext>if </mtext><mi>x</mi><mo>≥</mo><mo>+</mo><mn>3</mn><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>x</mi><mi mathvariant="normal">/</mi><mn>6</mn><mo>+</mo><mn>1</mn><mi mathvariant="normal">/</mi><mn>2</mn></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mtext>otherwise</mtext></mstyle></mtd></mtr></mtable></mrow></mrow><annotation encoding="application/x-tex">\text{Hardsigmoid}(x) = \begin{cases}
diff --git a/2.9/generated/torch.nn.functional.hardswish.html b/2.9/generated/torch.nn.functional.hardswish.html
index f95c5ec4225..32c8b689424 100644
--- a/2.9/generated/torch.nn.functional.hardswish.html
+++ b/2.9/generated/torch.nn.functional.hardswish.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.hardswish<a class="headerlink" href="#torch-nn-functional-hardswish" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.hardswish">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2394"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.hardswish" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2394"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.hardswish" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply hardswish function, element-wise.</p>
 <p>Follows implementation as described in the paper:
 <a class="reference external" href="https://arxiv.org/abs/1905.02244">Searching for MobileNetV3</a>.</p>
diff --git a/2.9/generated/torch.nn.functional.hardtanh.html b/2.9/generated/torch.nn.functional.hardtanh.html
index 2e747cd6ac0..236fc8e44f9 100644
--- a/2.9/generated/torch.nn.functional.hardtanh.html
+++ b/2.9/generated/torch.nn.functional.hardtanh.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.hardtanh<a class="headerlink" href="#torch-nn-functional-hardtanh" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.hardtanh">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">hardtanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1738"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.hardtanh" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">hardtanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1738"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.hardtanh" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the HardTanh function element-wise. See <a class="reference internal" href="torch.nn.Hardtanh.html#torch.nn.Hardtanh" title="torch.nn.Hardtanh"><code class="xref py py-class docutils literal notranslate"><span class="pre">Hardtanh</span></code></a> for more
 details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.hinge_embedding_loss.html b/2.9/generated/torch.nn.functional.hinge_embedding_loss.html
index f294eecdfbb..43a107d6b91 100644
--- a/2.9/generated/torch.nn.functional.hinge_embedding_loss.html
+++ b/2.9/generated/torch.nn.functional.hinge_embedding_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.hinge_embedding_loss<a class="headerlink" href="#torch-nn-functional-hinge-embedding-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.hinge_embedding_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">hinge_embedding_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3941"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.hinge_embedding_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">hinge_embedding_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3941"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.hinge_embedding_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the hinge embedding loss.</p>
 <p>See <a class="reference internal" href="torch.nn.HingeEmbeddingLoss.html#torch.nn.HingeEmbeddingLoss" title="torch.nn.HingeEmbeddingLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">HingeEmbeddingLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.huber_loss.html b/2.9/generated/torch.nn.functional.huber_loss.html
index 2f95d0a8897..57dadde7eb0 100644
--- a/2.9/generated/torch.nn.functional.huber_loss.html
+++ b/2.9/generated/torch.nn.functional.huber_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.huber_loss<a class="headerlink" href="#torch-nn-functional-huber-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.huber_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">huber_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3662"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.huber_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">huber_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3662"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.huber_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the Huber loss, with optional weighting.</p>
 <p>Function uses a squared term if the absolute
 element-wise error falls below delta and a delta-scaled L1 term otherwise.</p>
diff --git a/2.9/generated/torch.nn.functional.instance_norm.html b/2.9/generated/torch.nn.functional.instance_norm.html
index e5727a02e1b..3ade945385a 100644
--- a/2.9/generated/torch.nn.functional.instance_norm.html
+++ b/2.9/generated/torch.nn.functional.instance_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.instance_norm<a class="headerlink" href="#torch-nn-functional-instance-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.instance_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">instance_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">running_mean</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">running_var</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_input_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2837"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.instance_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">instance_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">running_mean</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">running_var</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_input_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2837"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.instance_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply Instance Normalization independently for each channel in every data sample within a batch.</p>
 <p>See <a class="reference internal" href="torch.nn.InstanceNorm1d.html#torch.nn.InstanceNorm1d" title="torch.nn.InstanceNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm1d</span></code></a>, <a class="reference internal" href="torch.nn.InstanceNorm2d.html#torch.nn.InstanceNorm2d" title="torch.nn.InstanceNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm2d</span></code></a>,
 <a class="reference internal" href="torch.nn.InstanceNorm3d.html#torch.nn.InstanceNorm3d" title="torch.nn.InstanceNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm3d</span></code></a> for details.</p>
diff --git a/2.9/generated/torch.nn.functional.interpolate.html b/2.9/generated/torch.nn.functional.interpolate.html
index b3a0c7de06a..9ea93d021e5 100644
--- a/2.9/generated/torch.nn.functional.interpolate.html
+++ b/2.9/generated/torch.nn.functional.interpolate.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.interpolate<a class="headerlink" href="#torch-nn-functional-interpolate" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.interpolate">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">interpolate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompute_scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">antialias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4530"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.interpolate" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">interpolate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompute_scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">antialias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4530"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.interpolate" title="Permalink to this definition">#</a></dt>
 <dd><p>Down/up samples the input.</p>
 <p>Tensor interpolated to either the given <code class="xref py py-attr docutils literal notranslate"><span class="pre">size</span></code> or the given
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale_factor</span></code></p>
diff --git a/2.9/generated/torch.nn.functional.kl_div.html b/2.9/generated/torch.nn.functional.kl_div.html
index 825ae4987c4..883a3c745b5 100644
--- a/2.9/generated/torch.nn.functional.kl_div.html
+++ b/2.9/generated/torch.nn.functional.kl_div.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.kl_div<a class="headerlink" href="#torch-nn-functional-kl-div" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.kl_div">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">kl_div</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3299"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.kl_div" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">kl_div</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3299"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.kl_div" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the KL Divergence loss.</p>
 <p>Refer - The <a class="reference external" href="https://en.wikipedia.org/wiki/Kullback-Leibler_divergence">Kullback-Leibler divergence Loss</a></p>
 <p>See <a class="reference internal" href="torch.nn.KLDivLoss.html#torch.nn.KLDivLoss" title="torch.nn.KLDivLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">KLDivLoss</span></code></a> for details.</p>
diff --git a/2.9/generated/torch.nn.functional.l1_loss.html b/2.9/generated/torch.nn.functional.l1_loss.html
index b6cacb7b4e1..2f3afd90518 100644
--- a/2.9/generated/torch.nn.functional.l1_loss.html
+++ b/2.9/generated/torch.nn.functional.l1_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.l1_loss<a class="headerlink" href="#torch-nn-functional-l1-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.l1_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">l1_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3742"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.l1_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">l1_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3742"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.l1_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the L1 loss, with optional weighting.</p>
 <p>Function that takes the mean element-wise absolute value difference.</p>
 <p>See <a class="reference internal" href="torch.nn.L1Loss.html#torch.nn.L1Loss" title="torch.nn.L1Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">L1Loss</span></code></a> for details.</p>
diff --git a/2.9/generated/torch.nn.functional.layer_norm.html b/2.9/generated/torch.nn.functional.layer_norm.html
index 80ac32d4d09..5965e8cf95e 100644
--- a/2.9/generated/torch.nn.functional.layer_norm.html
+++ b/2.9/generated/torch.nn.functional.layer_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.layer_norm<a class="headerlink" href="#torch-nn-functional-layer-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.layer_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">layer_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.layer_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">layer_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.layer_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply Layer Normalization for last certain number of dimensions.</p>
 <p>See <a class="reference internal" href="torch.nn.LayerNorm.html#torch.nn.LayerNorm" title="torch.nn.LayerNorm"><code class="xref py py-class docutils literal notranslate"><span class="pre">LayerNorm</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.leaky_relu.html b/2.9/generated/torch.nn.functional.leaky_relu.html
index 816a4b6149a..0f31f9a0738 100644
--- a/2.9/generated/torch.nn.functional.leaky_relu.html
+++ b/2.9/generated/torch.nn.functional.leaky_relu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.leaky_relu<a class="headerlink" href="#torch-nn-functional-leaky-relu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.leaky_relu">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">leaky_relu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1875"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.leaky_relu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">leaky_relu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1875"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.leaky_relu" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies element-wise,
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>LeakyReLU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mtext>negative_slope</mtext><mo>∗</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{LeakyReLU}(x) = \max(0, x) + \text{negative\_slope} * \min(0, x)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">LeakyReLU</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1.0044em;vertical-align:-0.31em;"></span><span class="mord text"><span class="mord">negative_slope</span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">∗</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">min</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span></span></p>
 <p>See <a class="reference internal" href="torch.nn.LeakyReLU.html#torch.nn.LeakyReLU" title="torch.nn.LeakyReLU"><code class="xref py py-class docutils literal notranslate"><span class="pre">LeakyReLU</span></code></a> for more details.</p>
diff --git a/2.9/generated/torch.nn.functional.local_response_norm.html b/2.9/generated/torch.nn.functional.local_response_norm.html
index 3ca49ad88d1..6de39f4468f 100644
--- a/2.9/generated/torch.nn.functional.local_response_norm.html
+++ b/2.9/generated/torch.nn.functional.local_response_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.local_response_norm<a class="headerlink" href="#torch-nn-functional-local-response-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.local_response_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">local_response_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2961"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.local_response_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">local_response_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2961"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.local_response_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply local response normalization over an input signal.</p>
 <p>The input signal is composed of several input planes, where channels occupy the second dimension.
 Normalization is applied across channels.</p>
diff --git a/2.9/generated/torch.nn.functional.log_softmax.html b/2.9/generated/torch.nn.functional.log_softmax.html
index 0ec3f489ac9..778f92188ad 100644
--- a/2.9/generated/torch.nn.functional.log_softmax.html
+++ b/2.9/generated/torch.nn.functional.log_softmax.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.log_softmax<a class="headerlink" href="#torch-nn-functional-log-softmax" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.log_softmax">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">log_softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.log_softmax" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">log_softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.log_softmax" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a softmax followed by a logarithm.</p>
 <p>While mathematically equivalent to log(softmax(x)), doing these two
 operations separately is slower and numerically unstable. This function
diff --git a/2.9/generated/torch.nn.functional.lp_pool1d.html b/2.9/generated/torch.nn.functional.lp_pool1d.html
index 9010df60d4b..2c503169762 100644
--- a/2.9/generated/torch.nn.functional.lp_pool1d.html
+++ b/2.9/generated/torch.nn.functional.lp_pool1d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.lp_pool1d<a class="headerlink" href="#torch-nn-functional-lp-pool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.lp_pool1d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">lp_pool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.lp_pool1d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">lp_pool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.lp_pool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a 1D power-average pooling over an input signal composed of several input planes.</p>
 <p>If the sum of all inputs to the power of <cite>p</cite> is
 zero, the gradient is set to zero as well.</p>
diff --git a/2.9/generated/torch.nn.functional.lp_pool2d.html b/2.9/generated/torch.nn.functional.lp_pool2d.html
index e2355fce751..2ccd2b2bdf9 100644
--- a/2.9/generated/torch.nn.functional.lp_pool2d.html
+++ b/2.9/generated/torch.nn.functional.lp_pool2d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.lp_pool2d<a class="headerlink" href="#torch-nn-functional-lp-pool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.lp_pool2d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">lp_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.lp_pool2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">lp_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1107"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.lp_pool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a 2D power-average pooling over an input signal composed of several input planes.</p>
 <p>If the sum of all inputs to the power of <cite>p</cite> is
 zero, the gradient is set to zero as well.</p>
diff --git a/2.9/generated/torch.nn.functional.lp_pool3d.html b/2.9/generated/torch.nn.functional.lp_pool3d.html
index ca92b04ad18..363b6298710 100644
--- a/2.9/generated/torch.nn.functional.lp_pool3d.html
+++ b/2.9/generated/torch.nn.functional.lp_pool3d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.lp_pool3d<a class="headerlink" href="#torch-nn-functional-lp-pool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.lp_pool3d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">lp_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.lp_pool3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">lp_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.lp_pool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a 3D power-average pooling over an input signal composed of several input planes.</p>
 <p>If the sum of all inputs to the power of <cite>p</cite> is
 zero, the gradient is set to zero as well.</p>
diff --git a/2.9/generated/torch.nn.functional.margin_ranking_loss.html b/2.9/generated/torch.nn.functional.margin_ranking_loss.html
index 94e94975abb..e1559b930c2 100644
--- a/2.9/generated/torch.nn.functional.margin_ranking_loss.html
+++ b/2.9/generated/torch.nn.functional.margin_ranking_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.margin_ranking_loss<a class="headerlink" href="#torch-nn-functional-margin-ranking-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.margin_ranking_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">margin_ranking_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3890"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.margin_ranking_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">margin_ranking_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3890"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.margin_ranking_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the margin ranking loss.</p>
 <p>See <a class="reference internal" href="torch.nn.MarginRankingLoss.html#torch.nn.MarginRankingLoss" title="torch.nn.MarginRankingLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">MarginRankingLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.max_pool1d.html b/2.9/generated/torch.nn.functional.max_pool1d.html
index 4f73c77dcfb..c6571813d9a 100644
--- a/2.9/generated/torch.nn.functional.max_pool1d.html
+++ b/2.9/generated/torch.nn.functional.max_pool1d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.max_pool1d<a class="headerlink" href="#torch-nn-functional-max-pool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.max_pool1d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_pool1d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_pool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D max pooling over an input signal composed of several input
 planes.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.nn.functional.max_pool2d.html b/2.9/generated/torch.nn.functional.max_pool2d.html
index 87f4bb9bd50..06d81f6b1a0 100644
--- a/2.9/generated/torch.nn.functional.max_pool2d.html
+++ b/2.9/generated/torch.nn.functional.max_pool2d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.max_pool2d<a class="headerlink" href="#torch-nn-functional-max-pool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.max_pool2d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_pool2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_pool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D max pooling over an input signal composed of several input
 planes.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.nn.functional.max_pool3d.html b/2.9/generated/torch.nn.functional.max_pool3d.html
index 27d7d11c186..f47031c342c 100644
--- a/2.9/generated/torch.nn.functional.max_pool3d.html
+++ b/2.9/generated/torch.nn.functional.max_pool3d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.max_pool3d<a class="headerlink" href="#torch-nn-functional-max-pool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.max_pool3d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_pool3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_pool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_pool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D max pooling over an input signal composed of several input
 planes.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.nn.functional.max_unpool1d.html b/2.9/generated/torch.nn.functional.max_unpool1d.html
index 31ac489a455..381eae72d2b 100644
--- a/2.9/generated/torch.nn.functional.max_unpool1d.html
+++ b/2.9/generated/torch.nn.functional.max_unpool1d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.max_unpool1d<a class="headerlink" href="#torch-nn-functional-max-unpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.max_unpool1d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_unpool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L964"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_unpool1d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_unpool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L964"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_unpool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute a partial inverse of <code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool1d</span></code>.</p>
 <p>See <a class="reference internal" href="torch.nn.MaxUnpool1d.html#torch.nn.MaxUnpool1d" title="torch.nn.MaxUnpool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool1d</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.max_unpool2d.html b/2.9/generated/torch.nn.functional.max_unpool2d.html
index c61769886cb..565f5dc153b 100644
--- a/2.9/generated/torch.nn.functional.max_unpool2d.html
+++ b/2.9/generated/torch.nn.functional.max_unpool2d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.max_unpool2d<a class="headerlink" href="#torch-nn-functional-max-unpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.max_unpool2d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_unpool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1003"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_unpool2d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_unpool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1003"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_unpool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute a partial inverse of <code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool2d</span></code>.</p>
 <p>See <a class="reference internal" href="torch.nn.MaxUnpool2d.html#torch.nn.MaxUnpool2d" title="torch.nn.MaxUnpool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool2d</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.max_unpool3d.html b/2.9/generated/torch.nn.functional.max_unpool3d.html
index 4e89f977b5b..ad3199a40b2 100644
--- a/2.9/generated/torch.nn.functional.max_unpool3d.html
+++ b/2.9/generated/torch.nn.functional.max_unpool3d.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.max_unpool3d<a class="headerlink" href="#torch-nn-functional-max-unpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.max_unpool3d">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_unpool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1036"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_unpool3d" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">max_unpool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1036"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.max_unpool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute a partial inverse of <code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool3d</span></code>.</p>
 <p>See <a class="reference internal" href="torch.nn.MaxUnpool3d.html#torch.nn.MaxUnpool3d" title="torch.nn.MaxUnpool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool3d</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.mish.html b/2.9/generated/torch.nn.functional.mish.html
index f8d73ea736a..63ee4974f3e 100644
--- a/2.9/generated/torch.nn.functional.mish.html
+++ b/2.9/generated/torch.nn.functional.mish.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.mish<a class="headerlink" href="#torch-nn-functional-mish" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.mish">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">mish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.mish" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">mish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.mish" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply the Mish function, element-wise.</p>
 <p>Mish: A Self Regularized Non-Monotonic Neural Activation Function.</p>
 <div class="math">
diff --git a/2.9/generated/torch.nn.functional.mse_loss.html b/2.9/generated/torch.nn.functional.mse_loss.html
index 88b7ff434cc..80391fc23ab 100644
--- a/2.9/generated/torch.nn.functional.mse_loss.html
+++ b/2.9/generated/torch.nn.functional.mse_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.mse_loss<a class="headerlink" href="#torch-nn-functional-mse-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.mse_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">mse_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3815"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.mse_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">mse_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3815"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.mse_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the element-wise mean squared error, with optional weighting.</p>
 <p>See <a class="reference internal" href="torch.nn.MSELoss.html#torch.nn.MSELoss" title="torch.nn.MSELoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">MSELoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.multi_margin_loss.html b/2.9/generated/torch.nn.functional.multi_margin_loss.html
index 1ab2ea59fe4..9cf7f66b888 100644
--- a/2.9/generated/torch.nn.functional.multi_margin_loss.html
+++ b/2.9/generated/torch.nn.functional.multi_margin_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.multi_margin_loss<a class="headerlink" href="#torch-nn-functional-multi-margin-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.multi_margin_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">multi_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.multi_margin_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">multi_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.multi_margin_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the multi margin loss, with optional weighting.</p>
 <p>See <a class="reference internal" href="torch.nn.MultiMarginLoss.html#torch.nn.MultiMarginLoss" title="torch.nn.MultiMarginLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">MultiMarginLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.multilabel_margin_loss.html b/2.9/generated/torch.nn.functional.multilabel_margin_loss.html
index 1a4da0f2ed4..3f0e9ed95f0 100644
--- a/2.9/generated/torch.nn.functional.multilabel_margin_loss.html
+++ b/2.9/generated/torch.nn.functional.multilabel_margin_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.multilabel_margin_loss<a class="headerlink" href="#torch-nn-functional-multilabel-margin-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.multilabel_margin_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">multilabel_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3985"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.multilabel_margin_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">multilabel_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3985"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.multilabel_margin_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the multilabel margin loss.</p>
 <p>See <a class="reference internal" href="torch.nn.MultiLabelMarginLoss.html#torch.nn.MultiLabelMarginLoss" title="torch.nn.MultiLabelMarginLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">MultiLabelMarginLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.multilabel_soft_margin_loss.html b/2.9/generated/torch.nn.functional.multilabel_soft_margin_loss.html
index c920ef53b6c..5a47ff0da3c 100644
--- a/2.9/generated/torch.nn.functional.multilabel_soft_margin_loss.html
+++ b/2.9/generated/torch.nn.functional.multilabel_soft_margin_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.multilabel_soft_margin_loss<a class="headerlink" href="#torch-nn-functional-multilabel-soft-margin-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.multilabel_soft_margin_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">multilabel_soft_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.multilabel_soft_margin_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">multilabel_soft_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.multilabel_soft_margin_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the multilabel soft margin loss.</p>
 <p>See <a class="reference internal" href="torch.nn.MultiLabelSoftMarginLoss.html#torch.nn.MultiLabelSoftMarginLoss" title="torch.nn.MultiLabelSoftMarginLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">MultiLabelSoftMarginLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.nll_loss.html b/2.9/generated/torch.nn.functional.nll_loss.html
index 708b2cecb52..8681ff4184c 100644
--- a/2.9/generated/torch.nn.functional.nll_loss.html
+++ b/2.9/generated/torch.nn.functional.nll_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.nll_loss<a class="headerlink" href="#torch-nn-functional-nll-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.nll_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">nll_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.nll_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">nll_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.nll_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the negative log likelihood loss.</p>
 <p>See <a class="reference internal" href="torch.nn.NLLLoss.html#torch.nn.NLLLoss" title="torch.nn.NLLLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">NLLLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.normalize.html b/2.9/generated/torch.nn.functional.normalize.html
index 55b63129577..223119a0c3d 100644
--- a/2.9/generated/torch.nn.functional.normalize.html
+++ b/2.9/generated/torch.nn.functional.normalize.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.normalize<a class="headerlink" href="#torch-nn-functional-normalize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.normalize">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">normalize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L5541"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.normalize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">normalize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L5541"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.normalize" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>L</mi><mi>p</mi></msub></mrow><annotation encoding="application/x-tex">L_p</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.9694em;vertical-align:-0.2861em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.1514em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">p</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2861em;"><span></span></span></span></span></span></span></span></span></span></span> normalization of inputs over specified dimension.</p>
 <p>For a tensor <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> of sizes <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><msub><mi>n</mi><mn>0</mn></msub><mo separator="true">,</mo><mi mathvariant="normal">.</mi><mi mathvariant="normal">.</mi><mi mathvariant="normal">.</mi><mo separator="true">,</mo><msub><mi>n</mi><mrow><mi>d</mi><mi>i</mi><mi>m</mi></mrow></msub><mo separator="true">,</mo><mi mathvariant="normal">.</mi><mi mathvariant="normal">.</mi><mi mathvariant="normal">.</mi><mo separator="true">,</mo><msub><mi>n</mi><mi>k</mi></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(n_0, ..., n_{dim}, ..., n_k)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord"><span class="mord mathnormal">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">0</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">...</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">d</span><span class="mord mathnormal mtight">im</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">...</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight" style="margin-right:0.03148em;">k</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span>, each
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>n</mi><mrow><mi>d</mi><mi>i</mi><mi>m</mi></mrow></msub></mrow><annotation encoding="application/x-tex">n_{dim}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">d</span><span class="mord mathnormal mtight">im</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> -element vector <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>v</mi></mrow><annotation encoding="application/x-tex">v</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">v</span></span></span></span></span> along dimension <code class="xref py py-attr docutils literal notranslate"><span class="pre">dim</span></code> is transformed as</p>
diff --git a/2.9/generated/torch.nn.functional.pad.html b/2.9/generated/torch.nn.functional.pad.html
index 45c6d755e6c..3e14f8747d5 100644
--- a/2.9/generated/torch.nn.functional.pad.html
+++ b/2.9/generated/torch.nn.functional.pad.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.pad<a class="headerlink" href="#torch-nn-functional-pad" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.pad">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">pad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'constant'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L5213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.pad" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">pad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'constant'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L5213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.pad" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads tensor.</p>
 <dl class="simple">
 <dt>Padding size:</dt><dd><p>The padding size by which to pad some dimensions of <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code>
diff --git a/2.9/generated/torch.nn.functional.poisson_nll_loss.html b/2.9/generated/torch.nn.functional.poisson_nll_loss.html
index 33624ec5e80..02a5b3b0fde 100644
--- a/2.9/generated/torch.nn.functional.poisson_nll_loss.html
+++ b/2.9/generated/torch.nn.functional.poisson_nll_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.poisson_nll_loss<a class="headerlink" href="#torch-nn-functional-poisson-nll-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.poisson_nll_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">poisson_nll_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.poisson_nll_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">poisson_nll_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.poisson_nll_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the Poisson negative log likelihood loss.</p>
 <p>See <a class="reference internal" href="torch.nn.PoissonNLLLoss.html#torch.nn.PoissonNLLLoss" title="torch.nn.PoissonNLLLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">PoissonNLLLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.relu.html b/2.9/generated/torch.nn.functional.relu.html
index 1269fd3adbd..dddaefad6fe 100644
--- a/2.9/generated/torch.nn.functional.relu.html
+++ b/2.9/generated/torch.nn.functional.relu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.relu<a class="headerlink" href="#torch-nn-functional-relu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.relu">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">relu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1686"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.relu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">relu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1686"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.relu" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the rectified linear unit function element-wise. See
 <a class="reference internal" href="torch.nn.ReLU.html#torch.nn.ReLU" title="torch.nn.ReLU"><code class="xref py py-class docutils literal notranslate"><span class="pre">ReLU</span></code></a> for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.relu6.html b/2.9/generated/torch.nn.functional.relu6.html
index 7dd7e7b3262..3bfc57dae92 100644
--- a/2.9/generated/torch.nn.functional.relu6.html
+++ b/2.9/generated/torch.nn.functional.relu6.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.relu6<a class="headerlink" href="#torch-nn-functional-relu6" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.relu6">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">relu6</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1773"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.relu6" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">relu6</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1773"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.relu6" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise function <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>ReLU6</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo separator="true">,</mo><mn>6</mn><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{ReLU6}(x) = \min(\max(0,x), 6)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">ReLU6</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">min</span><span class="mopen">(</span><span class="mop">max</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">6</span><span class="mclose">)</span></span></span></span></span>.</p>
 <p>See <a class="reference internal" href="torch.nn.ReLU6.html#torch.nn.ReLU6" title="torch.nn.ReLU6"><code class="xref py py-class docutils literal notranslate"><span class="pre">ReLU6</span></code></a> for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.rms_norm.html b/2.9/generated/torch.nn.functional.rms_norm.html
index 389d97e3d68..f2c8fad3b08 100644
--- a/2.9/generated/torch.nn.functional.rms_norm.html
+++ b/2.9/generated/torch.nn.functional.rms_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.rms_norm<a class="headerlink" href="#torch-nn-functional-rms-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.rms_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">rms_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2906"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.rms_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">rms_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2906"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.rms_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply Root Mean Square Layer Normalization.</p>
 <p>See <a class="reference internal" href="torch.nn.RMSNorm.html#torch.nn.RMSNorm" title="torch.nn.RMSNorm"><code class="xref py py-class docutils literal notranslate"><span class="pre">RMSNorm</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.rrelu.html b/2.9/generated/torch.nn.functional.rrelu.html
index 9ea07f56e35..0ae73c13faa 100644
--- a/2.9/generated/torch.nn.functional.rrelu.html
+++ b/2.9/generated/torch.nn.functional.rrelu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.rrelu<a class="headerlink" href="#torch-nn-functional-rrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.rrelu">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">rrelu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lower</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span> <span class="pre">/</span> <span class="pre">8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">upper</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span> <span class="pre">/</span> <span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1930"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.rrelu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">rrelu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lower</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span> <span class="pre">/</span> <span class="pre">8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">upper</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.</span> <span class="pre">/</span> <span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1930"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.rrelu" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomized leaky ReLU.</p>
 <p>See <a class="reference internal" href="torch.nn.RReLU.html#torch.nn.RReLU" title="torch.nn.RReLU"><code class="xref py py-class docutils literal notranslate"><span class="pre">RReLU</span></code></a> for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.selu.html b/2.9/generated/torch.nn.functional.selu.html
index 888fc4b115b..e821e4738c3 100644
--- a/2.9/generated/torch.nn.functional.selu.html
+++ b/2.9/generated/torch.nn.functional.selu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.selu<a class="headerlink" href="#torch-nn-functional-selu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.selu">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">selu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1813"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.selu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">selu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1813"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.selu" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies element-wise,
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>SELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>s</mi><mi>c</mi><mi>a</mi><mi>l</mi><mi>e</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>α</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{SELU}(x) = scale * (\max(0,x) + \min(0, \alpha * (\exp(x) - 1)))</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">SELU</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal">sc</span><span class="mord mathnormal">a</span><span class="mord mathnormal" style="margin-right:0.01968em;">l</span><span class="mord mathnormal">e</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">∗</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mop">max</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">min</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.0037em;">α</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">∗</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mop">exp</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">−</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord">1</span><span class="mclose">)))</span></span></span></span></span>,
 with <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>α</mi><mo>=</mo><mn>1.6732632423543772848170429916717</mn></mrow><annotation encoding="application/x-tex">\alpha=1.6732632423543772848170429916717</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal" style="margin-right:0.0037em;">α</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord">1.6732632423543772848170429916717</span></span></span></span></span> and
diff --git a/2.9/generated/torch.nn.functional.sigmoid.html b/2.9/generated/torch.nn.functional.sigmoid.html
index 8b925c3a654..971b0619919 100644
--- a/2.9/generated/torch.nn.functional.sigmoid.html
+++ b/2.9/generated/torch.nn.functional.sigmoid.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.sigmoid<a class="headerlink" href="#torch-nn-functional-sigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.sigmoid">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">sigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.sigmoid" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">sigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.sigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise function <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>Sigmoid</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mn>1</mn><mrow><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow></mfrac></mrow><annotation encoding="application/x-tex">\text{Sigmoid}(x) = \frac{1}{1 + \exp(-x)}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">Sigmoid</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.3651em;vertical-align:-0.52em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8451em;"><span style="top:-2.655em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">1</span><span class="mbin mtight">+</span><span class="mop mtight"><span class="mtight">e</span><span class="mtight">x</span><span class="mtight">p</span></span><span class="mopen mtight">(</span><span class="mord mtight">−</span><span class="mord mathnormal mtight">x</span><span class="mclose mtight">)</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.394em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">1</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.52em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span></span></span></span></span></p>
 <p>See <a class="reference internal" href="torch.nn.Sigmoid.html#torch.nn.Sigmoid" title="torch.nn.Sigmoid"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sigmoid</span></code></a> for more details.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.nn.functional.silu.html b/2.9/generated/torch.nn.functional.silu.html
index ecf462f790c..6ca8e980b31 100644
--- a/2.9/generated/torch.nn.functional.silu.html
+++ b/2.9/generated/torch.nn.functional.silu.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.silu<a class="headerlink" href="#torch-nn-functional-silu" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.silu">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">silu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.silu" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">silu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.silu" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply the Sigmoid Linear Unit (SiLU) function, element-wise.</p>
 <p>The SiLU function is also known as the swish function.</p>
 <div class="math">
diff --git a/2.9/generated/torch.nn.functional.smooth_l1_loss.html b/2.9/generated/torch.nn.functional.smooth_l1_loss.html
index 3e2fc55c882..fdf3c2ce7e5 100644
--- a/2.9/generated/torch.nn.functional.smooth_l1_loss.html
+++ b/2.9/generated/torch.nn.functional.smooth_l1_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.smooth_l1_loss<a class="headerlink" href="#torch-nn-functional-smooth-l1-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.smooth_l1_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">smooth_l1_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L3598"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.smooth_l1_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">smooth_l1_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L3598"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.smooth_l1_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the Smooth L1 loss.</p>
 <p>Function uses a squared term if the absolute
 element-wise error falls below beta and an L1 term otherwise.</p>
diff --git a/2.9/generated/torch.nn.functional.soft_margin_loss.html b/2.9/generated/torch.nn.functional.soft_margin_loss.html
index 6fe4ffbdd88..1b4909f407a 100644
--- a/2.9/generated/torch.nn.functional.soft_margin_loss.html
+++ b/2.9/generated/torch.nn.functional.soft_margin_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.soft_margin_loss<a class="headerlink" href="#torch-nn-functional-soft-margin-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.soft_margin_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">soft_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.soft_margin_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">soft_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.soft_margin_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the soft margin loss.</p>
 <p>See <a class="reference internal" href="torch.nn.SoftMarginLoss.html#torch.nn.SoftMarginLoss" title="torch.nn.SoftMarginLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">SoftMarginLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.softmax.html b/2.9/generated/torch.nn.functional.softmax.html
index 1723995851d..a759d7921e0 100644
--- a/2.9/generated/torch.nn.functional.softmax.html
+++ b/2.9/generated/torch.nn.functional.softmax.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.softmax<a class="headerlink" href="#torch-nn-functional-softmax" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.softmax">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2096"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.softmax" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2096"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.softmax" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a softmax function.</p>
 <p>Softmax is defined as:</p>
 <p><span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>Softmax</mtext><mo stretchy="false">(</mo><msub><mi>x</mi><mi>i</mi></msub><mo stretchy="false">)</mo><mo>=</mo><mfrac><mrow><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>x</mi><mi>i</mi></msub><mo stretchy="false">)</mo></mrow><mrow><msub><mo>∑</mo><mi>j</mi></msub><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>x</mi><mi>j</mi></msub><mo stretchy="false">)</mo></mrow></mfrac></mrow><annotation encoding="application/x-tex">\text{Softmax}(x_{i}) = \frac{\exp(x_i)}{\sum_j \exp(x_j)}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">Softmax</span></span><span class="mopen">(</span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3117em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">i</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.6772em;vertical-align:-0.6672em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.01em;"><span style="top:-2.655em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mop mtight"><span class="mop op-symbol small-op mtight" style="position:relative;top:0em;">∑</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.1496em;"><span style="top:-2.1786em;margin-left:0em;margin-right:0.0714em;"><span class="pstrut" style="height:2.5em;"></span><span class="sizing reset-size3 size1 mtight"><span class="mord mathnormal mtight" style="margin-right:0.05724em;">j</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.4603em;"><span></span></span></span></span></span></span><span class="mspace mtight" style="margin-right:0.1952em;"></span><span class="mop mtight"><span class="mtight">e</span><span class="mtight">x</span><span class="mtight">p</span></span><span class="mopen mtight">(</span><span class="mord mtight"><span class="mord mathnormal mtight">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3281em;"><span style="top:-2.357em;margin-left:0em;margin-right:0.0714em;"><span class="pstrut" style="height:2.5em;"></span><span class="sizing reset-size3 size1 mtight"><span class="mord mathnormal mtight" style="margin-right:0.05724em;">j</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2819em;"><span></span></span></span></span></span></span><span class="mclose mtight">)</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.485em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mop mtight"><span class="mtight">e</span><span class="mtight">x</span><span class="mtight">p</span></span><span class="mopen mtight">(</span><span class="mord mtight"><span class="mord mathnormal mtight">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3281em;"><span style="top:-2.357em;margin-left:0em;margin-right:0.0714em;"><span class="pstrut" style="height:2.5em;"></span><span class="sizing reset-size3 size1 mtight"><span class="mord mathnormal mtight">i</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.143em;"><span></span></span></span></span></span></span><span class="mclose mtight">)</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.6672em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span></span></span></span></span></p>
diff --git a/2.9/generated/torch.nn.functional.softmin.html b/2.9/generated/torch.nn.functional.softmin.html
index 6fa5b9f9941..dfe9a1c3a29 100644
--- a/2.9/generated/torch.nn.functional.softmin.html
+++ b/2.9/generated/torch.nn.functional.softmin.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.softmin<a class="headerlink" href="#torch-nn-functional-softmin" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.softmin">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">softmin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2063"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.softmin" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">softmin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2063"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.softmin" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a softmin function.</p>
 <p>Note that <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>Softmin</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mtext>Softmax</mtext><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{Softmin}(x) = \text{Softmax}(-x)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">Softmin</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">Softmax</span></span><span class="mopen">(</span><span class="mord">−</span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span></span>. See softmax definition for mathematical formula.</p>
 <p>See <a class="reference internal" href="torch.nn.Softmin.html#torch.nn.Softmin" title="torch.nn.Softmin"><code class="xref py py-class docutils literal notranslate"><span class="pre">Softmin</span></code></a> for more details.</p>
diff --git a/2.9/generated/torch.nn.functional.softsign.html b/2.9/generated/torch.nn.functional.softsign.html
index 03928e8d2b5..c56b56ff7cc 100644
--- a/2.9/generated/torch.nn.functional.softsign.html
+++ b/2.9/generated/torch.nn.functional.softsign.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.softsign<a class="headerlink" href="#torch-nn-functional-softsign" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.softsign">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">softsign</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2023"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.softsign" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">softsign</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2023"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.softsign" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies element-wise, the function <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>SoftSign</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mi>x</mi><mrow><mn>1</mn><mo>+</mo><mi mathvariant="normal">∣</mi><mi>x</mi><mi mathvariant="normal">∣</mi></mrow></mfrac></mrow><annotation encoding="application/x-tex">\text{SoftSign}(x) = \frac{x}{1 + |x|}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">SoftSign</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.2154em;vertical-align:-0.52em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.6954em;"><span style="top:-2.655em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">1</span><span class="mbin mtight">+</span><span class="mord mtight">∣</span><span class="mord mathnormal mtight">x</span><span class="mord mtight">∣</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.394em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">x</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.52em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span></span></span></span></span></p>
 <p>See <a class="reference internal" href="torch.nn.Softsign.html#torch.nn.Softsign" title="torch.nn.Softsign"><code class="xref py py-class docutils literal notranslate"><span class="pre">Softsign</span></code></a> for more details.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.nn.functional.tanh.html b/2.9/generated/torch.nn.functional.tanh.html
index ca11de8802a..6731ef49b01 100644
--- a/2.9/generated/torch.nn.functional.tanh.html
+++ b/2.9/generated/torch.nn.functional.tanh.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.tanh<a class="headerlink" href="#torch-nn-functional-tanh" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.tanh">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">tanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.tanh" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">tanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.tanh" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies element-wise,
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>Tanh</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mrow><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>−</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><mrow><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow></mfrac></mrow><annotation encoding="application/x-tex">\text{Tanh}(x) = \tanh(x) = \frac{\exp(x) - \exp(-x)}{\exp(x) + \exp(-x)}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">Tanh</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">tanh</span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.53em;vertical-align:-0.52em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.01em;"><span style="top:-2.655em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mop mtight"><span class="mtight">e</span><span class="mtight">x</span><span class="mtight">p</span></span><span class="mopen mtight">(</span><span class="mord mathnormal mtight">x</span><span class="mclose mtight">)</span><span class="mbin mtight">+</span><span class="mop mtight"><span class="mtight">e</span><span class="mtight">x</span><span class="mtight">p</span></span><span class="mopen mtight">(</span><span class="mord mtight">−</span><span class="mord mathnormal mtight">x</span><span class="mclose mtight">)</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.485em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mop mtight"><span class="mtight">e</span><span class="mtight">x</span><span class="mtight">p</span></span><span class="mopen mtight">(</span><span class="mord mathnormal mtight">x</span><span class="mclose mtight">)</span><span class="mbin mtight">−</span><span class="mop mtight"><span class="mtight">e</span><span class="mtight">x</span><span class="mtight">p</span></span><span class="mopen mtight">(</span><span class="mord mtight">−</span><span class="mord mathnormal mtight">x</span><span class="mclose mtight">)</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.52em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span></span></span></span></span></p>
 <p>See <a class="reference internal" href="torch.nn.Tanh.html#torch.nn.Tanh" title="torch.nn.Tanh"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tanh</span></code></a> for more details.</p>
diff --git a/2.9/generated/torch.nn.functional.tanhshrink.html b/2.9/generated/torch.nn.functional.tanhshrink.html
index 0b265f9d8a8..dc0db48f741 100644
--- a/2.9/generated/torch.nn.functional.tanhshrink.html
+++ b/2.9/generated/torch.nn.functional.tanhshrink.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.tanhshrink<a class="headerlink" href="#torch-nn-functional-tanhshrink" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.tanhshrink">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">tanhshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L2011"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.tanhshrink" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">tanhshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L2011"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.tanhshrink" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies element-wise, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>Tanhshrink</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>x</mi><mo>−</mo><mtext>Tanh</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{Tanhshrink}(x) = x - \text{Tanh}(x)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">Tanhshrink</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.6667em;vertical-align:-0.0833em;"></span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">−</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">Tanh</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span></span></p>
 <p>See <a class="reference internal" href="torch.nn.Tanhshrink.html#torch.nn.Tanhshrink" title="torch.nn.Tanhshrink"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tanhshrink</span></code></a> for more details.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.nn.functional.threshold.html b/2.9/generated/torch.nn.functional.threshold.html
index e3264109b96..085130297d2 100644
--- a/2.9/generated/torch.nn.functional.threshold.html
+++ b/2.9/generated/torch.nn.functional.threshold.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.threshold<a class="headerlink" href="#torch-nn-functional-threshold" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.threshold">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">threshold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L1650"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.threshold" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">threshold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L1650"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.threshold" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a threshold to each element of the input Tensor.</p>
 <p>See <a class="reference internal" href="torch.nn.Threshold.html#torch.nn.Threshold" title="torch.nn.Threshold"><code class="xref py py-class docutils literal notranslate"><span class="pre">Threshold</span></code></a> for more details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.torch.nn.parallel.data_parallel.html b/2.9/generated/torch.nn.functional.torch.nn.parallel.data_parallel.html
index 7bfc516e151..d478ed63bc3 100644
--- a/2.9/generated/torch.nn.functional.torch.nn.parallel.data_parallel.html
+++ b/2.9/generated/torch.nn.functional.torch.nn.parallel.data_parallel.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.torch.nn.parallel.data_parallel<a class="headerlink" href="#torch-nn-functional-torch-nn-parallel-data-parallel" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.parallel.data_parallel">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.parallel.</span></span><span class="sig-name descname"><span class="pre">data_parallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/data_parallel.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.data_parallel" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.parallel.</span></span><span class="sig-name descname"><span class="pre">data_parallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/data_parallel.py#L221"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.data_parallel" title="Permalink to this definition">#</a></dt>
 <dd><p>Evaluate module(input) in parallel across the GPUs given in device_ids.</p>
 <p>This is the functional version of the DataParallel module.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.triplet_margin_loss.html b/2.9/generated/torch.nn.functional.triplet_margin_loss.html
index e8fc7e701b9..0f13342dab1 100644
--- a/2.9/generated/torch.nn.functional.triplet_margin_loss.html
+++ b/2.9/generated/torch.nn.functional.triplet_margin_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.triplet_margin_loss<a class="headerlink" href="#torch-nn-functional-triplet-margin-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.triplet_margin_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">triplet_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L5422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.triplet_margin_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">triplet_margin_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L5422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.triplet_margin_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the triplet loss between given input tensors and a margin greater than 0.</p>
 <p>See <a class="reference internal" href="torch.nn.TripletMarginLoss.html#torch.nn.TripletMarginLoss" title="torch.nn.TripletMarginLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">TripletMarginLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.triplet_margin_with_distance_loss.html b/2.9/generated/torch.nn.functional.triplet_margin_with_distance_loss.html
index 6e8faa22774..30777fa65ed 100644
--- a/2.9/generated/torch.nn.functional.triplet_margin_with_distance_loss.html
+++ b/2.9/generated/torch.nn.functional.triplet_margin_with_distance_loss.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.triplet_margin_with_distance_loss<a class="headerlink" href="#torch-nn-functional-triplet-margin-with-distance-loss" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.triplet_margin_with_distance_loss">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">triplet_margin_with_distance_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">distance_function</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L5464"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.triplet_margin_with_distance_loss" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">triplet_margin_with_distance_loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">distance_function</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L5464"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.triplet_margin_with_distance_loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the triplet margin loss for input tensors using a custom distance function.</p>
 <p>See <a class="reference internal" href="torch.nn.TripletMarginWithDistanceLoss.html#torch.nn.TripletMarginWithDistanceLoss" title="torch.nn.TripletMarginWithDistanceLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">TripletMarginWithDistanceLoss</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.functional.unfold.html b/2.9/generated/torch.nn.functional.unfold.html
index ea65e6528e8..87ba81c4aef 100644
--- a/2.9/generated/torch.nn.functional.unfold.html
+++ b/2.9/generated/torch.nn.functional.unfold.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.unfold<a class="headerlink" href="#torch-nn-functional-unfold" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.unfold">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">unfold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L5582"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.unfold" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">unfold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L5582"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.unfold" title="Permalink to this definition">#</a></dt>
 <dd><p>Extract sliding local blocks from a batched input tensor.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.functional.upsample.html b/2.9/generated/torch.nn.functional.upsample.html
index 8c53ffe90f0..eb29f692708 100644
--- a/2.9/generated/torch.nn.functional.upsample.html
+++ b/2.9/generated/torch.nn.functional.upsample.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.upsample<a class="headerlink" href="#torch-nn-functional-upsample" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.upsample">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">upsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.upsample" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">upsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4389"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.upsample" title="Permalink to this definition">#</a></dt>
 <dd><p>Upsample input.</p>
 <p>Provided tensor is upsampled to either the given <code class="xref py py-attr docutils literal notranslate"><span class="pre">size</span></code> or the given
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale_factor</span></code></p>
diff --git a/2.9/generated/torch.nn.functional.upsample_bilinear.html b/2.9/generated/torch.nn.functional.upsample_bilinear.html
index 50ac02f583d..ada7c11562f 100644
--- a/2.9/generated/torch.nn.functional.upsample_bilinear.html
+++ b/2.9/generated/torch.nn.functional.upsample_bilinear.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.upsample_bilinear<a class="headerlink" href="#torch-nn-functional-upsample-bilinear" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.upsample_bilinear">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">upsample_bilinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4906"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.upsample_bilinear" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">upsample_bilinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4906"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.upsample_bilinear" title="Permalink to this definition">#</a></dt>
 <dd><p>Upsamples the input, using bilinear upsampling.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.functional.upsample_nearest.html b/2.9/generated/torch.nn.functional.upsample_nearest.html
index 6d60cf737fe..288b2fa7f72 100644
--- a/2.9/generated/torch.nn.functional.upsample_nearest.html
+++ b/2.9/generated/torch.nn.functional.upsample_nearest.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.functional.upsample_nearest<a class="headerlink" href="#torch-nn-functional-upsample-nearest" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.functional.upsample_nearest">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">upsample_nearest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/functional.py#L4838"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.upsample_nearest" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.functional.</span></span><span class="sig-name descname"><span class="pre">upsample_nearest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/functional.py#L4838"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.functional.upsample_nearest" title="Permalink to this definition">#</a></dt>
 <dd><p>Upsamples the input, using nearest neighbours’ pixel values.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.modules.activation.CELU.html b/2.9/generated/torch.nn.modules.activation.CELU.html
index 81b861b09bd..c21e9cb23fa 100644
--- a/2.9/generated/torch.nn.modules.activation.CELU.html
+++ b/2.9/generated/torch.nn.modules.activation.CELU.html
@@ -4415,7 +4415,7 @@
 <h1>CELU<a class="headerlink" href="#celu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.CELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">CELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.CELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">CELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.CELU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the CELU function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>CELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>α</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mi mathvariant="normal">/</mi><mi>α</mi><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{CELU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1))
@@ -4445,7 +4445,7 @@ <h1>CELU<a class="headerlink" href="#celu" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.CELU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L670"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.CELU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L670"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.CELU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4456,7 +4456,7 @@ <h1>CELU<a class="headerlink" href="#celu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.CELU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L664"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.CELU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L664"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.CELU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.ELU.html b/2.9/generated/torch.nn.modules.activation.ELU.html
index b7d638fce97..c05242a896a 100644
--- a/2.9/generated/torch.nn.modules.activation.ELU.html
+++ b/2.9/generated/torch.nn.modules.activation.ELU.html
@@ -4415,7 +4415,7 @@
 <h1>ELU<a class="headerlink" href="#elu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.ELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">ELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L573"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">ELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L573"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ELU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Exponential Linear Unit (ELU) function, element-wise.</p>
 <p>Method described in the paper: <a class="reference external" href="https://arxiv.org/abs/1511.07289">Fast and Accurate Deep Network Learning by Exponential Linear
 Units (ELUs)</a>.</p>
@@ -4450,7 +4450,7 @@ <h1>ELU<a class="headerlink" href="#elu" title="Permalink to this heading">#</a>
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.ELU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L619"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ELU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L619"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ELU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4461,7 +4461,7 @@ <h1>ELU<a class="headerlink" href="#elu" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.ELU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L613"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ELU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L613"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ELU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.GELU.html b/2.9/generated/torch.nn.modules.activation.GELU.html
index 047db6ce898..5573d18f17a 100644
--- a/2.9/generated/torch.nn.modules.activation.GELU.html
+++ b/2.9/generated/torch.nn.modules.activation.GELU.html
@@ -4415,7 +4415,7 @@
 <h1>GELU<a class="headerlink" href="#gelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.GELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">GELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">approximate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'none'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L777"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">GELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">approximate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'none'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L777"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GELU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Gaussian Error Linear Units function.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>GELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>x</mi><mo>∗</mo><mi mathvariant="normal">Φ</mi><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{GELU}(x) = x * \Phi(x)
@@ -4457,7 +4457,7 @@ <h1>GELU<a class="headerlink" href="#gelu" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.GELU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L818"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GELU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L818"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GELU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4468,7 +4468,7 @@ <h1>GELU<a class="headerlink" href="#gelu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.GELU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L812"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GELU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L812"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GELU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.GLU.html b/2.9/generated/torch.nn.modules.activation.GLU.html
index 964b9927c96..a30b79a79bc 100644
--- a/2.9/generated/torch.nn.modules.activation.GLU.html
+++ b/2.9/generated/torch.nn.modules.activation.GLU.html
@@ -4415,7 +4415,7 @@
 <h1>GLU<a class="headerlink" href="#glu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.GLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">GLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L734"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">GLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L734"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the gated linear unit function.</p>
 <p><span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mrow><mi>G</mi><mi>L</mi><mi>U</mi></mrow><mo stretchy="false">(</mo><mi>a</mi><mo separator="true">,</mo><mi>b</mi><mo stretchy="false">)</mo><mo>=</mo><mi>a</mi><mo>⊗</mo><mi>σ</mi><mo stretchy="false">(</mo><mi>b</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">{GLU}(a, b)= a \otimes \sigma(b)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal">G</span><span class="mord mathnormal" style="margin-right:0.10903em;">LU</span></span><span class="mopen">(</span><span class="mord mathnormal">a</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">b</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.6667em;vertical-align:-0.0833em;"></span><span class="mord mathnormal">a</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">⊗</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">σ</span><span class="mopen">(</span><span class="mord mathnormal">b</span><span class="mclose">)</span></span></span></span></span> where <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>a</mi></mrow><annotation encoding="application/x-tex">a</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">a</span></span></span></span></span> is the first half
 of the input matrices and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>b</mi></mrow><annotation encoding="application/x-tex">b</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal">b</span></span></span></span></span> is the second half.</p>
@@ -4441,7 +4441,7 @@ <h1>GLU<a class="headerlink" href="#glu" title="Permalink to this heading">#</a>
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.GLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L770"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L770"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4452,7 +4452,7 @@ <h1>GLU<a class="headerlink" href="#glu" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.GLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L764"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L764"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.GLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Hardshrink.html b/2.9/generated/torch.nn.modules.activation.Hardshrink.html
index 417dbf93c95..97d389151fe 100644
--- a/2.9/generated/torch.nn.modules.activation.Hardshrink.html
+++ b/2.9/generated/torch.nn.modules.activation.Hardshrink.html
@@ -4415,7 +4415,7 @@
 <h1>Hardshrink<a class="headerlink" href="#hardshrink" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardshrink">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Hardshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L825"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardshrink" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Hardshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L825"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardshrink" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Hard Shrinkage (Hardshrink) function element-wise.</p>
 <p>Hardshrink is defined as:</p>
 <div class="math">
@@ -4447,7 +4447,7 @@ <h1>Hardshrink<a class="headerlink" href="#hardshrink" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardshrink.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L867"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardshrink.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L867"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardshrink.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4458,7 +4458,7 @@ <h1>Hardshrink<a class="headerlink" href="#hardshrink" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardshrink.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L861"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardshrink.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L861"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardshrink.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Hardsigmoid.html b/2.9/generated/torch.nn.modules.activation.Hardsigmoid.html
index 40950880704..d9747a319d2 100644
--- a/2.9/generated/torch.nn.modules.activation.Hardsigmoid.html
+++ b/2.9/generated/torch.nn.modules.activation.Hardsigmoid.html
@@ -4415,7 +4415,7 @@
 <h1>Hardsigmoid<a class="headerlink" href="#hardsigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardsigmoid">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Hardsigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardsigmoid" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Hardsigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardsigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Hardsigmoid function element-wise.</p>
 <p>Hardsigmoid is defined as:</p>
 <div class="math">
@@ -4446,7 +4446,7 @@ <h1>Hardsigmoid<a class="headerlink" href="#hardsigmoid" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardsigmoid.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L398"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardsigmoid.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L398"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardsigmoid.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Hardswish.html b/2.9/generated/torch.nn.modules.activation.Hardswish.html
index aa6d1e836a0..63a83f9b95d 100644
--- a/2.9/generated/torch.nn.modules.activation.Hardswish.html
+++ b/2.9/generated/torch.nn.modules.activation.Hardswish.html
@@ -4415,7 +4415,7 @@
 <h1>Hardswish<a class="headerlink" href="#hardswish" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardswish">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardswish" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Hardswish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L528"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardswish" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Hardswish function, element-wise.</p>
 <p>Method described in the paper: <a class="reference external" href="https://arxiv.org/abs/1905.02244">Searching for MobileNetV3</a>.</p>
 <p>Hardswish is defined as:</p>
@@ -4447,7 +4447,7 @@ <h1>Hardswish<a class="headerlink" href="#hardswish" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardswish.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardswish.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L566"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardswish.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Hardtanh.html b/2.9/generated/torch.nn.modules.activation.Hardtanh.html
index e030e5c2873..d10300251f8 100644
--- a/2.9/generated/torch.nn.modules.activation.Hardtanh.html
+++ b/2.9/generated/torch.nn.modules.activation.Hardtanh.html
@@ -4415,7 +4415,7 @@
 <h1>Hardtanh<a class="headerlink" href="#hardtanh" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardtanh">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Hardtanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">min_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardtanh" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Hardtanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">min_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_val</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardtanh" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the HardTanh function element-wise.</p>
 <p>HardTanh is defined as:</p>
 <div class="math">
@@ -4452,7 +4452,7 @@ <h1>Hardtanh<a class="headerlink" href="#hardtanh" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardtanh.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardtanh.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardtanh.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4463,7 +4463,7 @@ <h1>Hardtanh<a class="headerlink" href="#hardtanh" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Hardtanh.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L288"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardtanh.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L288"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Hardtanh.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.LeakyReLU.html b/2.9/generated/torch.nn.modules.activation.LeakyReLU.html
index 3ea30f831a5..98d2395651a 100644
--- a/2.9/generated/torch.nn.modules.activation.LeakyReLU.html
+++ b/2.9/generated/torch.nn.modules.activation.LeakyReLU.html
@@ -4415,7 +4415,7 @@
 <h1>LeakyReLU<a class="headerlink" href="#leakyrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.LeakyReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">LeakyReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L874"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LeakyReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">LeakyReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">negative_slope</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L874"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LeakyReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the LeakyReLU function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>LeakyReLU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mtext>negative_slope</mtext><mo>∗</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{LeakyReLU}(x) = \max(0, x) + \text{negative\_slope} * \min(0, x)
@@ -4454,7 +4454,7 @@ <h1>LeakyReLU<a class="headerlink" href="#leakyrelu" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.LeakyReLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L924"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LeakyReLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L924"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LeakyReLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4465,7 +4465,7 @@ <h1>LeakyReLU<a class="headerlink" href="#leakyrelu" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.LeakyReLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L918"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LeakyReLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L918"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LeakyReLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.LogSigmoid.html b/2.9/generated/torch.nn.modules.activation.LogSigmoid.html
index 6fabbb1b13f..839b850be14 100644
--- a/2.9/generated/torch.nn.modules.activation.LogSigmoid.html
+++ b/2.9/generated/torch.nn.modules.activation.LogSigmoid.html
@@ -4415,7 +4415,7 @@
 <h1>LogSigmoid<a class="headerlink" href="#logsigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.LogSigmoid">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">LogSigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L932"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSigmoid" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">LogSigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L932"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Logsigmoid function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>LogSigmoid</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>log</mi><mo>⁡</mo><mrow><mo fence="true">(</mo><mfrac><mn>1</mn><mrow><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow></mfrac><mo fence="true">)</mo></mrow></mrow><annotation encoding="application/x-tex">\text{LogSigmoid}(x) = \log\left(\frac{ 1 }{ 1 + \exp(-x)}\right)
@@ -4438,7 +4438,7 @@ <h1>LogSigmoid<a class="headerlink" href="#logsigmoid" title="Permalink to this
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.LogSigmoid.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSigmoid.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSigmoid.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.LogSoftmax.html b/2.9/generated/torch.nn.modules.activation.LogSoftmax.html
index 2b32ba97d99..551ef110d95 100644
--- a/2.9/generated/torch.nn.modules.activation.LogSoftmax.html
+++ b/2.9/generated/torch.nn.modules.activation.LogSoftmax.html
@@ -4415,7 +4415,7 @@
 <h1>LogSoftmax<a class="headerlink" href="#logsoftmax" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.LogSoftmax">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">LogSoftmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSoftmax" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">LogSoftmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSoftmax" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>log</mi><mo>⁡</mo><mo stretchy="false">(</mo><mtext>Softmax</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\log(\text{Softmax}(x))</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">lo<span style="margin-right:0.01389em;">g</span></span><span class="mopen">(</span><span class="mord text"><span class="mord">Softmax</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">))</span></span></span></span></span> function to an n-dimensional input Tensor.</p>
 <p>The LogSoftmax formulation can be simplified as:</p>
 <div class="math">
@@ -4449,7 +4449,7 @@ <h1>LogSoftmax<a class="headerlink" href="#logsoftmax" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.LogSoftmax.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1898"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSoftmax.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1898"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSoftmax.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4460,7 +4460,7 @@ <h1>LogSoftmax<a class="headerlink" href="#logsoftmax" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.LogSoftmax.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1892"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSoftmax.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1892"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.LogSoftmax.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Mish.html b/2.9/generated/torch.nn.modules.activation.Mish.html
index 76b10c57fea..6978df5cdb2 100644
--- a/2.9/generated/torch.nn.modules.activation.Mish.html
+++ b/2.9/generated/torch.nn.modules.activation.Mish.html
@@ -4415,7 +4415,7 @@
 <h1>Mish<a class="headerlink" href="#mish" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Mish">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Mish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L483"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Mish" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Mish</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L483"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Mish" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Mish function, element-wise.</p>
 <p>Mish: A Self Regularized Non-Monotonic Neural Activation Function.</p>
 <div class="math">
@@ -4443,7 +4443,7 @@ <h1>Mish<a class="headerlink" href="#mish" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Mish.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Mish.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Mish.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4454,7 +4454,7 @@ <h1>Mish<a class="headerlink" href="#mish" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Mish.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L514"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Mish.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L514"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Mish.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.MultiheadAttention.html b/2.9/generated/torch.nn.modules.activation.MultiheadAttention.html
index fa34c3e1784..2c412e8084e 100644
--- a/2.9/generated/torch.nn.modules.activation.MultiheadAttention.html
+++ b/2.9/generated/torch.nn.modules.activation.MultiheadAttention.html
@@ -4415,7 +4415,7 @@
 <h1>MultiheadAttention<a class="headerlink" href="#multiheadattention" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.MultiheadAttention">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">MultiheadAttention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embed_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_heads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_bias_kv</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_zero_attn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1085"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.MultiheadAttention" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">MultiheadAttention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embed_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_heads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_bias_kv</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">add_zero_attn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1085"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.MultiheadAttention" title="Permalink to this definition">#</a></dt>
 <dd><p>Allows the model to jointly attend to information from different representation subspaces.</p>
 <p>This MultiheadAttention layer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4478,7 +4478,7 @@ <h1>MultiheadAttention<a class="headerlink" href="#multiheadattention" title="Pe
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.MultiheadAttention.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">need_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">average_attn_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1252"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.MultiheadAttention.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">need_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">average_attn_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1252"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.MultiheadAttention.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute attention outputs using query, key, and value embeddings.</p>
 <blockquote>
 <div><p>Supports optional parameters for padding, masks and attention weights.</p>
@@ -4554,7 +4554,7 @@ <h1>MultiheadAttention<a class="headerlink" href="#multiheadattention" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.MultiheadAttention.merge_masks">
-<span class="sig-name descname"><span class="pre">merge_masks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1514"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.MultiheadAttention.merge_masks" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">merge_masks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_padding_mask</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">query</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1514"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.MultiheadAttention.merge_masks" title="Permalink to this definition">#</a></dt>
 <dd><p>Determine mask type and combine masks if necessary.</p>
 <p>If only one mask is provided, that mask
 and the corresponding mask type will be returned. If both masks are provided, they will be both
diff --git a/2.9/generated/torch.nn.modules.activation.PReLU.html b/2.9/generated/torch.nn.modules.activation.PReLU.html
index 63b9c6bcbd9..e02422b896c 100644
--- a/2.9/generated/torch.nn.modules.activation.PReLU.html
+++ b/2.9/generated/torch.nn.modules.activation.PReLU.html
@@ -4415,7 +4415,7 @@
 <h1>PReLU<a class="headerlink" href="#prelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.PReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">PReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1565"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.PReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">PReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.25</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1565"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.PReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise PReLU function.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>PReLU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>a</mi><mo>∗</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{PReLU}(x) = \max(0,x) + a * \min(0,x)
@@ -4472,7 +4472,7 @@ <h1>PReLU<a class="headerlink" href="#prelu" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.PReLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1640"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.PReLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1640"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.PReLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4483,7 +4483,7 @@ <h1>PReLU<a class="headerlink" href="#prelu" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.PReLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1634"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.PReLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1634"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.PReLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4494,7 +4494,7 @@ <h1>PReLU<a class="headerlink" href="#prelu" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.PReLU.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1628"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.PReLU.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1628"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.PReLU.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.activation.RReLU.html b/2.9/generated/torch.nn.modules.activation.RReLU.html
index 36cdc40f017..fa3496607cd 100644
--- a/2.9/generated/torch.nn.modules.activation.RReLU.html
+++ b/2.9/generated/torch.nn.modules.activation.RReLU.html
@@ -4415,7 +4415,7 @@
 <h1>RReLU<a class="headerlink" href="#rrelu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.RReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">RReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lower</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.125</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">upper</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3333333333333333</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.RReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">RReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lower</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.125</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">upper</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3333333333333333</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.RReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the randomized leaky rectified linear unit function, element-wise.</p>
 <p>Method described in the paper:
 <a class="reference external" href="https://arxiv.org/abs/1505.00853">Empirical Evaluation of Rectified Activations in Convolutional Network</a>.</p>
@@ -4455,7 +4455,7 @@ <h1>RReLU<a class="headerlink" href="#rrelu" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.RReLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.RReLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.RReLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4466,7 +4466,7 @@ <h1>RReLU<a class="headerlink" href="#rrelu" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.RReLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.RReLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.RReLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.ReLU.html b/2.9/generated/torch.nn.modules.activation.ReLU.html
index 619703e4049..03cdaa13b22 100644
--- a/2.9/generated/torch.nn.modules.activation.ReLU.html
+++ b/2.9/generated/torch.nn.modules.activation.ReLU.html
@@ -4415,7 +4415,7 @@
 <h1>ReLU<a class="headerlink" href="#relu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.ReLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">ReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">ReLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the rectified linear unit function element-wise.</p>
 <p><span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>ReLU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mo stretchy="false">(</mo><mi>x</mi><msup><mo stretchy="false">)</mo><mo>+</mo></msup><mo>=</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{ReLU}(x) = (x)^+ = \max(0, x)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord text"><span class="mord">ReLU</span></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose">)</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.0213em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal">x</span><span class="mclose"><span class="mclose">)</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.7713em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mbin mtight">+</span></span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">x</span><span class="mclose">)</span></span></span></span></span></p>
 <dl class="field-list simple">
@@ -4446,7 +4446,7 @@ <h1>ReLU<a class="headerlink" href="#relu" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.ReLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L146"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4457,7 +4457,7 @@ <h1>ReLU<a class="headerlink" href="#relu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.ReLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.ReLU6.html b/2.9/generated/torch.nn.modules.activation.ReLU6.html
index 47b6f6d89ca..c5d009b7821 100644
--- a/2.9/generated/torch.nn.modules.activation.ReLU6.html
+++ b/2.9/generated/torch.nn.modules.activation.ReLU6.html
@@ -4415,7 +4415,7 @@
 <h1>ReLU6<a class="headerlink" href="#relu6" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.ReLU6">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">ReLU6</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU6" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">ReLU6</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU6" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the ReLU6 function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>ReLU6</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo separator="true">,</mo><mn>6</mn><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{ReLU6}(x) = \min(\max(0,x), 6)
@@ -4441,7 +4441,7 @@ <h1>ReLU6<a class="headerlink" href="#relu6" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.ReLU6.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU6.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.ReLU6.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.SELU.html b/2.9/generated/torch.nn.modules.activation.SELU.html
index ffb21e4c041..2fc696e49ca 100644
--- a/2.9/generated/torch.nn.modules.activation.SELU.html
+++ b/2.9/generated/torch.nn.modules.activation.SELU.html
@@ -4415,7 +4415,7 @@
 <h1>SELU<a class="headerlink" href="#selu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.SELU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">SELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SELU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">SELU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SELU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the SELU function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>SELU</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mtext>scale</mtext><mo>∗</mo><mo stretchy="false">(</mo><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>x</mi><mo stretchy="false">)</mo><mo>+</mo><mi>min</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mi>α</mi><mo>∗</mo><mo stretchy="false">(</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{SELU}(x) = \text{scale} * (\max(0,x) + \min(0, \alpha * (\exp(x) - 1)))
@@ -4451,7 +4451,7 @@ <h1>SELU<a class="headerlink" href="#selu" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.SELU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L726"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SELU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L726"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SELU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4462,7 +4462,7 @@ <h1>SELU<a class="headerlink" href="#selu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.SELU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L720"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SELU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L720"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SELU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.SiLU.html b/2.9/generated/torch.nn.modules.activation.SiLU.html
index 7138ebbd7ae..3553b3c155d 100644
--- a/2.9/generated/torch.nn.modules.activation.SiLU.html
+++ b/2.9/generated/torch.nn.modules.activation.SiLU.html
@@ -4415,7 +4415,7 @@
 <h1>SiLU<a class="headerlink" href="#silu" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.SiLU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">SiLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L433"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SiLU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">SiLU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L433"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SiLU" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Sigmoid Linear Unit (SiLU) function, element-wise.</p>
 <p>The SiLU function is also known as the swish function.</p>
 <div class="math">
@@ -4448,7 +4448,7 @@ <h1>SiLU<a class="headerlink" href="#silu" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.SiLU.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L475"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SiLU.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L475"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SiLU.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4459,7 +4459,7 @@ <h1>SiLU<a class="headerlink" href="#silu" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.SiLU.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L469"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SiLU.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L469"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.SiLU.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Sigmoid.html b/2.9/generated/torch.nn.modules.activation.Sigmoid.html
index 8686ec321c9..05d19718a83 100644
--- a/2.9/generated/torch.nn.modules.activation.Sigmoid.html
+++ b/2.9/generated/torch.nn.modules.activation.Sigmoid.html
@@ -4415,7 +4415,7 @@
 <h1>Sigmoid<a class="headerlink" href="#sigmoid" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Sigmoid">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Sigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L335"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Sigmoid" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Sigmoid</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L335"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Sigmoid" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Sigmoid function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>Sigmoid</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mn>1</mn><mrow><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mo>−</mo><mi>x</mi><mo stretchy="false">)</mo></mrow></mfrac></mrow><annotation encoding="application/x-tex">\text{Sigmoid}(x) = \sigma(x) = \frac{1}{1 + \exp(-x)}
@@ -4438,7 +4438,7 @@ <h1>Sigmoid<a class="headerlink" href="#sigmoid" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Sigmoid.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L355"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Sigmoid.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L355"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Sigmoid.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Softmax.html b/2.9/generated/torch.nn.modules.activation.Softmax.html
index c1e2d8f5c18..503ca6f9e67 100644
--- a/2.9/generated/torch.nn.modules.activation.Softmax.html
+++ b/2.9/generated/torch.nn.modules.activation.Softmax.html
@@ -4415,7 +4415,7 @@
 <h1>Softmax<a class="headerlink" href="#softmax" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softmax">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1755"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softmax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1755"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Softmax function to an n-dimensional input Tensor.</p>
 <p>Rescales them so that the elements of the n-dimensional output Tensor
 lie in the range [0,1] and sum to 1.</p>
@@ -4460,7 +4460,7 @@ <h1>Softmax<a class="headerlink" href="#softmax" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softmax.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1813"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1813"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4471,7 +4471,7 @@ <h1>Softmax<a class="headerlink" href="#softmax" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softmax.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Softmax2d.html b/2.9/generated/torch.nn.modules.activation.Softmax2d.html
index 9f851dddf94..7c033838fa4 100644
--- a/2.9/generated/torch.nn.modules.activation.Softmax2d.html
+++ b/2.9/generated/torch.nn.modules.activation.Softmax2d.html
@@ -4415,7 +4415,7 @@
 <h1>Softmax2d<a class="headerlink" href="#softmax2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softmax2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softmax2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1820"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softmax2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1820"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies SoftMax over features to each spatial location.</p>
 <p>When given an image of <code class="docutils literal notranslate"><span class="pre">Channels</span> <span class="pre">x</span> <span class="pre">Height</span> <span class="pre">x</span> <span class="pre">Width</span></code>, it will
 apply <cite>Softmax</cite> to each location <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>C</mi><mi>h</mi><mi>a</mi><mi>n</mi><mi>n</mi><mi>e</mi><mi>l</mi><mi>s</mi><mo separator="true">,</mo><msub><mi>h</mi><mi>i</mi></msub><mo separator="true">,</mo><msub><mi>w</mi><mi>j</mi></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(Channels, h_i, w_j)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1.0361em;vertical-align:-0.2861em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mord mathnormal">hann</span><span class="mord mathnormal">e</span><span class="mord mathnormal" style="margin-right:0.01968em;">l</span><span class="mord mathnormal">s</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal">h</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3117em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">i</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02691em;">w</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3117em;"><span style="top:-2.55em;margin-left:-0.0269em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight" style="margin-right:0.05724em;">j</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2861em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span></p>
@@ -4444,7 +4444,7 @@ <h1>Softmax2d<a class="headerlink" href="#softmax2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softmax2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1842"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1842"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmax2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Softmin.html b/2.9/generated/torch.nn.modules.activation.Softmin.html
index ddd6f357206..c12b8ea6359 100644
--- a/2.9/generated/torch.nn.modules.activation.Softmin.html
+++ b/2.9/generated/torch.nn.modules.activation.Softmin.html
@@ -4415,7 +4415,7 @@
 <h1>Softmin<a class="headerlink" href="#softmin" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softmin">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softmin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1699"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmin" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softmin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1699"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmin" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Softmin function to an n-dimensional input Tensor.</p>
 <p>Rescales them so that the elements of the n-dimensional output Tensor
 lie in the range <cite>[0, 1]</cite> and sum to 1.</p>
@@ -4452,7 +4452,7 @@ <h1>Softmin<a class="headerlink" href="#softmin" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softmin.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1748"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmin.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1748"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmin.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4463,7 +4463,7 @@ <h1>Softmin<a class="headerlink" href="#softmin" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softmin.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1742"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmin.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1742"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softmin.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Softplus.html b/2.9/generated/torch.nn.modules.activation.Softplus.html
index f20792f437d..d2b15008e0b 100644
--- a/2.9/generated/torch.nn.modules.activation.Softplus.html
+++ b/2.9/generated/torch.nn.modules.activation.Softplus.html
@@ -4415,7 +4415,7 @@
 <h1>Softplus<a class="headerlink" href="#softplus" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softplus">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softplus</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L958"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softplus" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softplus</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L958"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softplus" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Softplus function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>Softplus</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mn>1</mn><mi>β</mi></mfrac><mo>∗</mo><mi>log</mi><mo>⁡</mo><mo stretchy="false">(</mo><mn>1</mn><mo>+</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>β</mi><mo>∗</mo><mi>x</mi><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{Softplus}(x) = \frac{1}{\beta} * \log(1 + \exp(\beta * x))
@@ -4448,7 +4448,7 @@ <h1>Softplus<a class="headerlink" href="#softplus" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softplus.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1002"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softplus.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1002"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softplus.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4459,7 +4459,7 @@ <h1>Softplus<a class="headerlink" href="#softplus" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softplus.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L996"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softplus.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L996"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softplus.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Softshrink.html b/2.9/generated/torch.nn.modules.activation.Softshrink.html
index a0545d2e118..9df3a18b5d7 100644
--- a/2.9/generated/torch.nn.modules.activation.Softshrink.html
+++ b/2.9/generated/torch.nn.modules.activation.Softshrink.html
@@ -4415,7 +4415,7 @@
 <h1>Softshrink<a class="headerlink" href="#softshrink" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softshrink">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1009"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softshrink" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1009"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softshrink" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the soft shrinkage function element-wise.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>SoftShrinkage</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mrow><mo fence="true">{</mo><mtable rowspacing="0.36em" columnalign="left left" columnspacing="1em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>x</mi><mo>−</mo><mi>λ</mi><mo separator="true">,</mo></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mtext> if </mtext><mi>x</mi><mo>&gt;</mo><mi>λ</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>x</mi><mo>+</mo><mi>λ</mi><mo separator="true">,</mo></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mtext> if </mtext><mi>x</mi><mo>&lt;</mo><mo>−</mo><mi>λ</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mn>0</mn><mo separator="true">,</mo></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="false"><mtext> otherwise </mtext></mstyle></mtd></mtr></mtable></mrow></mrow><annotation encoding="application/x-tex">\text{SoftShrinkage}(x) =
@@ -4446,7 +4446,7 @@ <h1>Softshrink<a class="headerlink" href="#softshrink" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softshrink.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1049"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softshrink.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1049"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softshrink.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4457,7 +4457,7 @@ <h1>Softshrink<a class="headerlink" href="#softshrink" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softshrink.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softshrink.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1043"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softshrink.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Run forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Softsign.html b/2.9/generated/torch.nn.modules.activation.Softsign.html
index eae88fede5f..db8a4dfcfad 100644
--- a/2.9/generated/torch.nn.modules.activation.Softsign.html
+++ b/2.9/generated/torch.nn.modules.activation.Softsign.html
@@ -4415,7 +4415,7 @@
 <h1>Softsign<a class="headerlink" href="#softsign" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softsign">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softsign</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1647"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softsign" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Softsign</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1647"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softsign" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise Softsign function.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>SoftSign</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mfrac><mi>x</mi><mrow><mn>1</mn><mo>+</mo><mi mathvariant="normal">∣</mi><mi>x</mi><mi mathvariant="normal">∣</mi></mrow></mfrac></mrow><annotation encoding="application/x-tex">\text{SoftSign}(x) = \frac{x}{ 1 + |x|}
@@ -4438,7 +4438,7 @@ <h1>Softsign<a class="headerlink" href="#softsign" title="Permalink to this head
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Softsign.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softsign.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Softsign.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Tanh.html b/2.9/generated/torch.nn.modules.activation.Tanh.html
index 065103ad2d6..220e9f2102a 100644
--- a/2.9/generated/torch.nn.modules.activation.Tanh.html
+++ b/2.9/generated/torch.nn.modules.activation.Tanh.html
@@ -4415,7 +4415,7 @@
 <h1>Tanh<a class="headerlink" href="#tanh" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Tanh">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Tanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Tanh" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Tanh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L405"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Tanh" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the Hyperbolic Tangent (Tanh) function element-wise.</p>
 <p>Tanh is defined as:</p>
 <div class="math">
@@ -4439,7 +4439,7 @@ <h1>Tanh<a class="headerlink" href="#tanh" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Tanh.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Tanh.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Tanh.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Tanhshrink.html b/2.9/generated/torch.nn.modules.activation.Tanhshrink.html
index 4c4f3cbc575..2ade76d0256 100644
--- a/2.9/generated/torch.nn.modules.activation.Tanhshrink.html
+++ b/2.9/generated/torch.nn.modules.activation.Tanhshrink.html
@@ -4415,7 +4415,7 @@
 <h1>Tanhshrink<a class="headerlink" href="#tanhshrink" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Tanhshrink">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Tanhshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1673"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Tanhshrink" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Tanhshrink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1673"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Tanhshrink" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies the element-wise Tanhshrink function.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>Tanhshrink</mtext><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo><mo>=</mo><mi>x</mi><mo>−</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>x</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\text{Tanhshrink}(x) = x - \tanh(x)
@@ -4438,7 +4438,7 @@ <h1>Tanhshrink<a class="headerlink" href="#tanhshrink" title="Permalink to this
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Tanhshrink.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L1692"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Tanhshrink.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L1692"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Tanhshrink.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.activation.Threshold.html b/2.9/generated/torch.nn.modules.activation.Threshold.html
index d57c5f3afb6..c3c2b08695c 100644
--- a/2.9/generated/torch.nn.modules.activation.Threshold.html
+++ b/2.9/generated/torch.nn.modules.activation.Threshold.html
@@ -4415,7 +4415,7 @@
 <h1>Threshold<a class="headerlink" href="#threshold" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Threshold">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Threshold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Threshold" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.activation.</span></span><span class="sig-name descname"><span class="pre">Threshold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">threshold</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Threshold" title="Permalink to this definition">#</a></dt>
 <dd><p>Thresholds each element of the input Tensor.</p>
 <p>Threshold is defined as:</p>
 <div class="math">
@@ -4450,7 +4450,7 @@ <h1>Threshold<a class="headerlink" href="#threshold" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Threshold.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Threshold.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Threshold.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4461,7 +4461,7 @@ <h1>Threshold<a class="headerlink" href="#threshold" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.activation.Threshold.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/activation.py#L91"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Threshold.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/activation.py#L91"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.activation.Threshold.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.html b/2.9/generated/torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.html
index ed77874d97a..f23bc981085 100644
--- a/2.9/generated/torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.html
+++ b/2.9/generated/torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.html
@@ -4415,7 +4415,7 @@
 <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwithloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.adaptive.</span></span><span class="sig-name descname"><span class="pre">AdaptiveLogSoftmaxWithLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cutoffs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">div_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">head_bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.adaptive.</span></span><span class="sig-name descname"><span class="pre">AdaptiveLogSoftmaxWithLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_classes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cutoffs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">div_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">head_bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Efficient softmax approximation.</p>
 <p>As described in
 <a class="reference external" href="https://arxiv.org/abs/1609.04309">Efficient softmax approximation for GPUs by Edouard Grave, Armand Joulin,
@@ -4509,7 +4509,7 @@ <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwit
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4520,7 +4520,7 @@ <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwit
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.log_prob">
-<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.log_prob" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">log_prob</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.log_prob" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute log probabilities for all <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext mathvariant="monospace">n_classes</mtext></mrow><annotation encoding="application/x-tex">\texttt{n\_classes}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7063em;vertical-align:-0.0951em;"></span><span class="mord text"><span class="mord texttt">n_classes</span></span></span></span></span></span>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4546,7 +4546,7 @@ <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwit
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.predict">
-<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.predict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">predict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.predict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the class with the highest probability for each example in the input minibatch.</p>
 <p>This is equivalent to <code class="docutils literal notranslate"><span class="pre">self.log_prob(input).argmax(dim=1)</span></code>, but is more efficient in some cases.</p>
 <dl class="field-list simple">
@@ -4571,7 +4571,7 @@ <h1>AdaptiveLogSoftmaxWithLoss<a class="headerlink" href="#adaptivelogsoftmaxwit
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/adaptive.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/adaptive.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.batchnorm.BatchNorm1d.html b/2.9/generated/torch.nn.modules.batchnorm.BatchNorm1d.html
index e5c9a7949c1..457932e85b1 100644
--- a/2.9/generated/torch.nn.modules.batchnorm.BatchNorm1d.html
+++ b/2.9/generated/torch.nn.modules.batchnorm.BatchNorm1d.html
@@ -4415,7 +4415,7 @@
 <h1>BatchNorm1d<a class="headerlink" href="#batchnorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.BatchNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">BatchNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.BatchNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">BatchNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.BatchNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Batch Normalization over a 2D or 3D input.</p>
 <p>Method described in the paper
 <a class="reference external" href="https://arxiv.org/abs/1502.03167">Batch Normalization: Accelerating Deep Network Training by Reducing
diff --git a/2.9/generated/torch.nn.modules.batchnorm.BatchNorm2d.html b/2.9/generated/torch.nn.modules.batchnorm.BatchNorm2d.html
index bf406a4c217..6a17e31be93 100644
--- a/2.9/generated/torch.nn.modules.batchnorm.BatchNorm2d.html
+++ b/2.9/generated/torch.nn.modules.batchnorm.BatchNorm2d.html
@@ -4415,7 +4415,7 @@
 <h1>BatchNorm2d<a class="headerlink" href="#batchnorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.BatchNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">BatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.BatchNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">BatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.BatchNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Batch Normalization over a 4D input.</p>
 <p>4D is a mini-batch of 2D inputs
 with additional channel dimension. Method described in the paper
diff --git a/2.9/generated/torch.nn.modules.batchnorm.BatchNorm3d.html b/2.9/generated/torch.nn.modules.batchnorm.BatchNorm3d.html
index 57a24dc3dea..710ee7e8c3c 100644
--- a/2.9/generated/torch.nn.modules.batchnorm.BatchNorm3d.html
+++ b/2.9/generated/torch.nn.modules.batchnorm.BatchNorm3d.html
@@ -4415,7 +4415,7 @@
 <h1>BatchNorm3d<a class="headerlink" href="#batchnorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.BatchNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">BatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L491"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.BatchNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">BatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L491"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.BatchNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Batch Normalization over a 5D input.</p>
 <p>5D is a mini-batch of 3D inputs with additional channel dimension as described in the paper
 <a class="reference external" href="https://arxiv.org/abs/1502.03167">Batch Normalization: Accelerating Deep Network Training by Reducing
diff --git a/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm1d.html b/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm1d.html
index 694d15f8d6d..e370dae15c8 100644
--- a/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm1d.html
+++ b/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm1d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyBatchNorm1d<a class="headerlink" href="#lazybatchnorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.LazyBatchNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L346"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L346"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.BatchNorm1d.html#torch.nn.BatchNorm1d" title="torch.nn.BatchNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.BatchNorm1d</span></code></a> module with lazy initialization.</p>
 <p>Lazy initialization based on the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm1d.html#torch.nn.modules.batchnorm.BatchNorm1d" title="torch.nn.modules.batchnorm.BatchNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm1d</span></code></a> that is inferred
 from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4444,7 +4444,7 @@ <h1>LazyBatchNorm1d<a class="headerlink" href="#lazybatchnorm1d" title="Permalin
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.LazyBatchNorm1d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm1d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L270"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm1d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm1d.html#torch.nn.modules.batchnorm.BatchNorm1d" title="torch.nn.modules.batchnorm.BatchNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm1d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm2d.html b/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm2d.html
index 623dcba2157..8c9bbcd18d0 100644
--- a/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm2d.html
+++ b/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm2d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyBatchNorm2d<a class="headerlink" href="#lazybatchnorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.LazyBatchNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L457"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L457"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.BatchNorm2d.html#torch.nn.BatchNorm2d" title="torch.nn.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.BatchNorm2d</span></code></a> module with lazy initialization.</p>
 <p>Lazy initialization is done for the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm2d.html#torch.nn.modules.batchnorm.BatchNorm2d" title="torch.nn.modules.batchnorm.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm2d</span></code></a> that is inferred
 from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4444,7 +4444,7 @@ <h1>LazyBatchNorm2d<a class="headerlink" href="#lazybatchnorm2d" title="Permalin
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.LazyBatchNorm2d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm2d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L380"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm2d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm2d.html#torch.nn.modules.batchnorm.BatchNorm2d" title="torch.nn.modules.batchnorm.BatchNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm2d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm3d.html b/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm3d.html
index ec86483aa93..b5e5136a65f 100644
--- a/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm3d.html
+++ b/2.9/generated/torch.nn.modules.batchnorm.LazyBatchNorm3d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyBatchNorm3d<a class="headerlink" href="#lazybatchnorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.LazyBatchNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L568"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">LazyBatchNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L568"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.BatchNorm3d.html#torch.nn.BatchNorm3d" title="torch.nn.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.BatchNorm3d</span></code></a> module with lazy initialization.</p>
 <p>Lazy initialization is done for the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm3d.html#torch.nn.modules.batchnorm.BatchNorm3d" title="torch.nn.modules.batchnorm.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm3d</span></code></a> that is inferred
 from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4444,7 +4444,7 @@ <h1>LazyBatchNorm3d<a class="headerlink" href="#lazybatchnorm3d" title="Permalin
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.LazyBatchNorm3d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L491"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm3d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L491"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.LazyBatchNorm3d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.batchnorm.BatchNorm3d.html#torch.nn.modules.batchnorm.BatchNorm3d" title="torch.nn.modules.batchnorm.BatchNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchNorm3d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.batchnorm.SyncBatchNorm.html b/2.9/generated/torch.nn.modules.batchnorm.SyncBatchNorm.html
index b3b20731d1a..e7013d80475 100644
--- a/2.9/generated/torch.nn.modules.batchnorm.SyncBatchNorm.html
+++ b/2.9/generated/torch.nn.modules.batchnorm.SyncBatchNorm.html
@@ -4415,7 +4415,7 @@
 <h1>SyncBatchNorm<a class="headerlink" href="#syncbatchnorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.SyncBatchNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">SyncBatchNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.SyncBatchNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.batchnorm.</span></span><span class="sig-name descname"><span class="pre">SyncBatchNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L602"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.SyncBatchNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Batch Normalization over a N-Dimensional input.</p>
 <p>The N-D input is a mini-batch of [N-2]D inputs with additional channel dimension) as described in the paper
 <a class="reference external" href="https://arxiv.org/abs/1502.03167">Batch Normalization: Accelerating Deep Network Training by Reducing
@@ -4527,7 +4527,7 @@ <h1>SyncBatchNorm<a class="headerlink" href="#syncbatchnorm" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.SyncBatchNorm.convert_sync_batchnorm">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">convert_sync_batchnorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L828"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.SyncBatchNorm.convert_sync_batchnorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">convert_sync_batchnorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L828"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.SyncBatchNorm.convert_sync_batchnorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts all <code class="xref py py-attr docutils literal notranslate"><span class="pre">BatchNorm*D</span></code> layers in the model to <a class="reference internal" href="torch.nn.SyncBatchNorm.html#torch.nn.SyncBatchNorm" title="torch.nn.SyncBatchNorm"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.SyncBatchNorm</span></code></a> layers.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4566,7 +4566,7 @@ <h1>SyncBatchNorm<a class="headerlink" href="#syncbatchnorm" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.batchnorm.SyncBatchNorm.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/batchnorm.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.SyncBatchNorm.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/batchnorm.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.batchnorm.SyncBatchNorm.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.channelshuffle.ChannelShuffle.html b/2.9/generated/torch.nn.modules.channelshuffle.ChannelShuffle.html
index bdab1f37f27..c4c6b13fedb 100644
--- a/2.9/generated/torch.nn.modules.channelshuffle.ChannelShuffle.html
+++ b/2.9/generated/torch.nn.modules.channelshuffle.ChannelShuffle.html
@@ -4415,7 +4415,7 @@
 <h1>ChannelShuffle<a class="headerlink" href="#channelshuffle" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.channelshuffle.ChannelShuffle">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.channelshuffle.</span></span><span class="sig-name descname"><span class="pre">ChannelShuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">groups</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/channelshuffle.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.channelshuffle.ChannelShuffle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.channelshuffle.</span></span><span class="sig-name descname"><span class="pre">ChannelShuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">groups</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/channelshuffle.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.channelshuffle.ChannelShuffle" title="Permalink to this definition">#</a></dt>
 <dd><p>Divides and rearranges the channels in a tensor.</p>
 <p>This operation divides the channels in a tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mo>∗</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, *)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">∗</span><span class="mclose">)</span></span></span></span></span>
 into g groups as <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mfrac><mi>C</mi><mi>g</mi></mfrac><mo separator="true">,</mo><mi>g</mi><mo separator="true">,</mo><mo>∗</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, \frac{C}{g}, g, *)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1.3534em;vertical-align:-0.4811em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8723em;"><span style="top:-2.655em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight" style="margin-right:0.03588em;">g</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.394em;"><span class="pstrut" style="height:3em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight" style="margin-right:0.07153em;">C</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.4811em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">g</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">∗</span><span class="mclose">)</span></span></span></span></span> and shuffles them,
@@ -4451,7 +4451,7 @@ <h1>ChannelShuffle<a class="headerlink" href="#channelshuffle" title="Permalink
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.channelshuffle.ChannelShuffle.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/channelshuffle.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.channelshuffle.ChannelShuffle.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/channelshuffle.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.channelshuffle.ChannelShuffle.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4462,7 +4462,7 @@ <h1>ChannelShuffle<a class="headerlink" href="#channelshuffle" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.channelshuffle.ChannelShuffle.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/channelshuffle.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.channelshuffle.ChannelShuffle.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/channelshuffle.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.channelshuffle.ChannelShuffle.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.container.ModuleDict.html b/2.9/generated/torch.nn.modules.container.ModuleDict.html
index 59dc671f49b..cb1963d7f45 100644
--- a/2.9/generated/torch.nn.modules.container.ModuleDict.html
+++ b/2.9/generated/torch.nn.modules.container.ModuleDict.html
@@ -4415,7 +4415,7 @@
 <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleDict">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">ModuleDict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">ModuleDict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds submodules in a dictionary.</p>
 <p><a class="reference internal" href="torch.nn.ModuleDict.html#torch.nn.ModuleDict" title="torch.nn.ModuleDict"><code class="xref py py-class docutils literal notranslate"><span class="pre">ModuleDict</span></code></a> can be indexed like a regular Python dictionary,
 but modules it contains are properly registered, and will be visible by all
@@ -4456,7 +4456,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleDict.clear">
-<span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L569"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.clear" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L569"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.clear" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove all items from the ModuleDict.</p>
 <dl class="field-list simple">
 </dl>
@@ -4464,7 +4464,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleDict.items">
-<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L588"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.items" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L588"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.items" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ModuleDict key/value pairs.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4475,7 +4475,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleDict.keys">
-<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.keys" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.keys" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ModuleDict keys.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4486,7 +4486,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleDict.pop">
-<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L573"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L573"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.pop" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove key from the ModuleDict and return its module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4500,7 +4500,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleDict.update">
-<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L598"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.update" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L598"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.update" title="Permalink to this definition">#</a></dt>
 <dd><p>Update the <a class="reference internal" href="torch.nn.ModuleDict.html#torch.nn.ModuleDict" title="torch.nn.ModuleDict"><code class="xref py py-class docutils literal notranslate"><span class="pre">ModuleDict</span></code></a> with key-value pairs from a mapping, overwriting existing keys.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4517,7 +4517,7 @@ <h1>ModuleDict<a class="headerlink" href="#moduledict" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleDict.values">
-<span class="sig-name descname"><span class="pre">values</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L593"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.values" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">values</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L593"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleDict.values" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ModuleDict values.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.container.ModuleList.html b/2.9/generated/torch.nn.modules.container.ModuleList.html
index 27d903b1d70..a56c108725c 100644
--- a/2.9/generated/torch.nn.modules.container.ModuleList.html
+++ b/2.9/generated/torch.nn.modules.container.ModuleList.html
@@ -4415,7 +4415,7 @@
 <h1>ModuleList<a class="headerlink" href="#modulelist" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleList">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">ModuleList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleList" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">ModuleList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleList" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds submodules in a list.</p>
 <p><a class="reference internal" href="torch.nn.ModuleList.html#torch.nn.ModuleList" title="torch.nn.ModuleList"><code class="xref py py-class docutils literal notranslate"><span class="pre">ModuleList</span></code></a> can be indexed like a regular Python list, but
 modules it contains are properly registered, and will be visible by all
@@ -4440,7 +4440,7 @@ <h1>ModuleList<a class="headerlink" href="#modulelist" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleList.append">
-<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L465"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleList.append" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L465"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleList.append" title="Permalink to this definition">#</a></dt>
 <dd><p>Append a given module to the end of the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4454,7 +4454,7 @@ <h1>ModuleList<a class="headerlink" href="#modulelist" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleList.extend">
-<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L479"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleList.extend" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L479"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleList.extend" title="Permalink to this definition">#</a></dt>
 <dd><p>Append modules from a Python iterable to the end of the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4468,7 +4468,7 @@ <h1>ModuleList<a class="headerlink" href="#modulelist" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ModuleList.insert">
-<span class="sig-name descname"><span class="pre">insert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleList.insert" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">insert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ModuleList.insert" title="Permalink to this definition">#</a></dt>
 <dd><p>Insert a given module before a given index in the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.modules.container.ParameterDict.html b/2.9/generated/torch.nn.modules.container.ParameterDict.html
index 4be79b6eeb8..7b77a2db193 100644
--- a/2.9/generated/torch.nn.modules.container.ParameterDict.html
+++ b/2.9/generated/torch.nn.modules.container.ParameterDict.html
@@ -4415,7 +4415,7 @@
 <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">ParameterDict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L785"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">ParameterDict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L785"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds parameters in a dictionary.</p>
 <p>ParameterDict can be indexed like a regular Python dictionary, but Parameters it
 contains are properly registered, and will be visible by all Module methods.
@@ -4453,7 +4453,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.clear">
-<span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L895"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.clear" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clear</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L895"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.clear" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove all items from the ParameterDict.</p>
 <dl class="field-list simple">
 </dl>
@@ -4461,7 +4461,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.copy">
-<span class="sig-name descname"><span class="pre">copy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L871"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.copy" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">copy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L871"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.copy" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a copy of this <a class="reference internal" href="torch.nn.ParameterDict.html#torch.nn.ParameterDict" title="torch.nn.ParameterDict"><code class="xref py py-class docutils literal notranslate"><span class="pre">ParameterDict</span></code></a> instance.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4472,7 +4472,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.fromkeys">
-<span class="sig-name descname"><span class="pre">fromkeys</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L928"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.fromkeys" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fromkeys</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L928"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.fromkeys" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a new ParameterDict with the keys provided.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4489,7 +4489,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.get">
-<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L919"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.get" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L919"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.get" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the parameter associated with key if present. Otherwise return default if provided, None if not.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4506,7 +4506,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.items">
-<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L943"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.items" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">items</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L943"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.items" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ParameterDict key/value pairs.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4517,7 +4517,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.keys">
-<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L939"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.keys" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">keys</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L939"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.keys" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ParameterDict keys.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4528,7 +4528,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.pop">
-<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L900"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L900"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.pop" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove key from the ParameterDict and return its parameter.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4542,7 +4542,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.popitem">
-<span class="sig-name descname"><span class="pre">popitem</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.popitem" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">popitem</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.popitem" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove and return the last inserted <cite>(key, parameter)</cite> pair from the ParameterDict.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4553,7 +4553,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.setdefault">
-<span class="sig-name descname"><span class="pre">setdefault</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.setdefault" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">setdefault</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L880"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.setdefault" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the default for a key in the Parameterdict.</p>
 <p>If key is in the ParameterDict, return its value.
 If not, insert <cite>key</cite> with a parameter <cite>default</cite> and return <cite>default</cite>.
@@ -4573,7 +4573,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.update">
-<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.update" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.update" title="Permalink to this definition">#</a></dt>
 <dd><p>Update the <a class="reference internal" href="torch.nn.ParameterDict.html#torch.nn.ParameterDict" title="torch.nn.ParameterDict"><code class="xref py py-class docutils literal notranslate"><span class="pre">ParameterDict</span></code></a> with key-value pairs from <code class="docutils literal notranslate"><span class="pre">parameters</span></code>, overwriting existing keys.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4591,7 +4591,7 @@ <h1>ParameterDict<a class="headerlink" href="#parameterdict" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterDict.values">
-<span class="sig-name descname"><span class="pre">values</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L947"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.values" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">values</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L947"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterDict.values" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterable of the ParameterDict values.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.container.ParameterList.html b/2.9/generated/torch.nn.modules.container.ParameterList.html
index 7f566175dc7..1c68e673635 100644
--- a/2.9/generated/torch.nn.modules.container.ParameterList.html
+++ b/2.9/generated/torch.nn.modules.container.ParameterList.html
@@ -4415,7 +4415,7 @@
 <h1>ParameterList<a class="headerlink" href="#parameterlist" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterList">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">ParameterList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L638"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterList" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">ParameterList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L638"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterList" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds parameters in a list.</p>
 <p><a class="reference internal" href="torch.nn.ParameterList.html#torch.nn.ParameterList" title="torch.nn.ParameterList"><code class="xref py py-class docutils literal notranslate"><span class="pre">ParameterList</span></code></a> can be used like a regular Python
 list, but Tensors that are <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> are properly registered,
@@ -4445,7 +4445,7 @@ <h1>ParameterList<a class="headerlink" href="#parameterlist" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterList.append">
-<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L725"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterList.append" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L725"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterList.append" title="Permalink to this definition">#</a></dt>
 <dd><p>Append a given value at the end of the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4459,7 +4459,7 @@ <h1>ParameterList<a class="headerlink" href="#parameterlist" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterList.extend">
-<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterList.extend" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterList.extend" title="Permalink to this definition">#</a></dt>
 <dd><p>Append values from a Python iterable to the end of the list.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4473,7 +4473,7 @@ <h1>ParameterList<a class="headerlink" href="#parameterlist" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.ParameterList.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterList.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.ParameterList.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.container.Sequential.html b/2.9/generated/torch.nn.modules.container.Sequential.html
index 6975c3339b3..95b0789c8cb 100644
--- a/2.9/generated/torch.nn.modules.container.Sequential.html
+++ b/2.9/generated/torch.nn.modules.container.Sequential.html
@@ -4415,7 +4415,7 @@
 <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.container.Sequential">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">Sequential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">Sequential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.container.</span></span><span class="sig-name descname"><span class="pre">Sequential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">arg</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.html#collections.OrderedDict" title="(in Python v3.14)"><span class="pre">OrderedDict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.modules.module.Module"><span class="pre">Module</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span></dt>
 <dd><p>A sequential container.</p>
@@ -4461,7 +4461,7 @@ <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.Sequential.append">
-<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L253"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.append" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">append</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L253"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.append" title="Permalink to this definition">#</a></dt>
 <dd><p>Append a given module to the end.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4486,7 +4486,7 @@ <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.Sequential.extend">
-<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequential</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.extend" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequential</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L306"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.extend" title="Permalink to this definition">#</a></dt>
 <dd><p>Extends the current Sequential container with layers from another Sequential container.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4513,13 +4513,13 @@ <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.Sequential.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.Sequential.insert">
-<span class="sig-name descname"><span class="pre">insert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.insert" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">insert</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">index</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.insert" title="Permalink to this definition">#</a></dt>
 <dd><p>Inserts a module into the Sequential container at the specified index.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4547,7 +4547,7 @@ <h1>Sequential<a class="headerlink" href="#sequential" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.container.Sequential.pop">
-<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/container.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/container.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.container.Sequential.pop" title="Permalink to this definition">#</a></dt>
 <dd><p>Pop <code class="docutils literal notranslate"><span class="pre">key</span></code> from self.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.conv.Conv1d.html b/2.9/generated/torch.nn.modules.conv.Conv1d.html
index f63edea6bdd..e10dd18a2c9 100644
--- a/2.9/generated/torch.nn.modules.conv.Conv1d.html
+++ b/2.9/generated/torch.nn.modules.conv.Conv1d.html
@@ -4415,7 +4415,7 @@
 <h1>Conv1d<a class="headerlink" href="#conv1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.Conv1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">Conv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.Conv1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">Conv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.Conv1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D convolution over an input signal composed of several input
 planes.</p>
 <p>In the simplest case, the output value of the layer with input size
diff --git a/2.9/generated/torch.nn.modules.conv.Conv2d.html b/2.9/generated/torch.nn.modules.conv.Conv2d.html
index aa8bf10e2b7..1fc250826a8 100644
--- a/2.9/generated/torch.nn.modules.conv.Conv2d.html
+++ b/2.9/generated/torch.nn.modules.conv.Conv2d.html
@@ -4415,7 +4415,7 @@
 <h1>Conv2d<a class="headerlink" href="#conv2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.Conv2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">Conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.Conv2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">Conv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.Conv2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D convolution over an input signal composed of several input
 planes.</p>
 <p>In the simplest case, the output value of the layer with input size
diff --git a/2.9/generated/torch.nn.modules.conv.Conv3d.html b/2.9/generated/torch.nn.modules.conv.Conv3d.html
index 358746016a6..61ea01099aa 100644
--- a/2.9/generated/torch.nn.modules.conv.Conv3d.html
+++ b/2.9/generated/torch.nn.modules.conv.Conv3d.html
@@ -4415,7 +4415,7 @@
 <h1>Conv3d<a class="headerlink" href="#conv3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.Conv3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">Conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.Conv3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">Conv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.Conv3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D convolution over an input signal composed of several input
 planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><msub><mi>C</mi><mrow><mi>i</mi><mi>n</mi></mrow></msub><mo separator="true">,</mo><mi>D</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C_{in}, D, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3117em;"><span style="top:-2.55em;margin-left:-0.0715em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">in</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>
diff --git a/2.9/generated/torch.nn.modules.conv.ConvTranspose1d.html b/2.9/generated/torch.nn.modules.conv.ConvTranspose1d.html
index 566effdd296..3e22b21f099 100644
--- a/2.9/generated/torch.nn.modules.conv.ConvTranspose1d.html
+++ b/2.9/generated/torch.nn.modules.conv.ConvTranspose1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvTranspose1d<a class="headerlink" href="#convtranspose1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.ConvTranspose1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.ConvTranspose1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.ConvTranspose1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D transposed convolution operator over an input image
 composed of several input planes.</p>
 <p>This module can be seen as the gradient of Conv1d with respect to its input.
diff --git a/2.9/generated/torch.nn.modules.conv.ConvTranspose2d.html b/2.9/generated/torch.nn.modules.conv.ConvTranspose2d.html
index 7ca6eeb941c..1e5129905c4 100644
--- a/2.9/generated/torch.nn.modules.conv.ConvTranspose2d.html
+++ b/2.9/generated/torch.nn.modules.conv.ConvTranspose2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvTranspose2d<a class="headerlink" href="#convtranspose2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.ConvTranspose2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L976"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.ConvTranspose2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L976"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.ConvTranspose2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D transposed convolution operator over an input image
 composed of several input planes.</p>
 <p>This module can be seen as the gradient of Conv2d with respect to its input.
@@ -4593,7 +4593,7 @@ <h1>ConvTranspose2d<a class="headerlink" href="#convtranspose2d" title="Permalin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.ConvTranspose2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1133"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.ConvTranspose2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1133"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.ConvTranspose2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Variables</dt>
diff --git a/2.9/generated/torch.nn.modules.conv.ConvTranspose3d.html b/2.9/generated/torch.nn.modules.conv.ConvTranspose3d.html
index 4b235811c85..79b15726ae9 100644
--- a/2.9/generated/torch.nn.modules.conv.ConvTranspose3d.html
+++ b/2.9/generated/torch.nn.modules.conv.ConvTranspose3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConvTranspose3d<a class="headerlink" href="#convtranspose3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.ConvTranspose3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.ConvTranspose3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">ConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.ConvTranspose3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D transposed convolution operator over an input image composed of several input
 planes.
 The transposed convolution operator multiplies each input value element-wise by a learnable kernel,
diff --git a/2.9/generated/torch.nn.modules.conv.LazyConv1d.html b/2.9/generated/torch.nn.modules.conv.LazyConv1d.html
index 88ceac416c8..cf1a23af925 100644
--- a/2.9/generated/torch.nn.modules.conv.LazyConv1d.html
+++ b/2.9/generated/torch.nn.modules.conv.LazyConv1d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyConv1d<a class="headerlink" href="#lazyconv1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConv1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConv1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.Conv1d.html#torch.nn.Conv1d" title="torch.nn.Conv1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Conv1d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.modules.conv.Conv1d.html#torch.nn.modules.conv.Conv1d" title="torch.nn.modules.conv.Conv1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv1d</span></code></a> is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite> and <cite>bias</cite>.</p>
@@ -4446,7 +4446,7 @@ <h1>LazyConv1d<a class="headerlink" href="#lazyconv1d" title="Permalink to this
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConv1d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv1d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv1d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.Conv1d.html#torch.nn.modules.conv.Conv1d" title="torch.nn.modules.conv.Conv1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv1d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.conv.LazyConv2d.html b/2.9/generated/torch.nn.modules.conv.LazyConv2d.html
index bb81e1bcd10..f4e75cdc0bb 100644
--- a/2.9/generated/torch.nn.modules.conv.LazyConv2d.html
+++ b/2.9/generated/torch.nn.modules.conv.LazyConv2d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyConv2d<a class="headerlink" href="#lazyconv2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConv2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1521"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConv2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1521"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.Conv2d.html#torch.nn.Conv2d" title="torch.nn.Conv2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Conv2d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.modules.conv.Conv2d.html#torch.nn.modules.conv.Conv2d" title="torch.nn.modules.conv.Conv2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv2d</span></code></a> that is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite> and <cite>bias</cite>.</p>
@@ -4446,7 +4446,7 @@ <h1>LazyConv2d<a class="headerlink" href="#lazyconv2d" title="Permalink to this
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConv2d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv2d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv2d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.Conv2d.html#torch.nn.modules.conv.Conv2d" title="torch.nn.modules.conv.Conv2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv2d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.conv.LazyConv3d.html b/2.9/generated/torch.nn.modules.conv.LazyConv3d.html
index d1425bafeb0..dd3a4a0b973 100644
--- a/2.9/generated/torch.nn.modules.conv.LazyConv3d.html
+++ b/2.9/generated/torch.nn.modules.conv.LazyConv3d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyConv3d<a class="headerlink" href="#lazyconv3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConv3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1590"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConv3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1590"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.Conv3d.html#torch.nn.Conv3d" title="torch.nn.Conv3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Conv3d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.modules.conv.Conv3d.html#torch.nn.modules.conv.Conv3d" title="torch.nn.modules.conv.Conv3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv3d</span></code></a> that is inferred from
 the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4447,7 +4447,7 @@ <h1>LazyConv3d<a class="headerlink" href="#lazyconv3d" title="Permalink to this
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConv3d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv3d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConv3d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.Conv3d.html#torch.nn.modules.conv.Conv3d" title="torch.nn.modules.conv.Conv3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">Conv3d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.conv.LazyConvTranspose1d.html b/2.9/generated/torch.nn.modules.conv.LazyConvTranspose1d.html
index 05db1129c10..c4bb8ce331c 100644
--- a/2.9/generated/torch.nn.modules.conv.LazyConvTranspose1d.html
+++ b/2.9/generated/torch.nn.modules.conv.LazyConvTranspose1d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyConvTranspose1d<a class="headerlink" href="#lazyconvtranspose1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConvTranspose1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.ConvTranspose1d.html#torch.nn.ConvTranspose1d" title="torch.nn.ConvTranspose1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.ConvTranspose1d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose1d.html#torch.nn.modules.conv.ConvTranspose1d" title="torch.nn.modules.conv.ConvTranspose1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose1d</span></code></a> that is inferred from
 the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4444,7 +4444,7 @@ <h1>LazyConvTranspose1d<a class="headerlink" href="#lazyconvtranspose1d" title="
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConvTranspose1d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose1d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose1d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose1d.html#torch.nn.modules.conv.ConvTranspose1d" title="torch.nn.modules.conv.ConvTranspose1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose1d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.conv.LazyConvTranspose2d.html b/2.9/generated/torch.nn.modules.conv.LazyConvTranspose2d.html
index fc16ece3626..11815addfda 100644
--- a/2.9/generated/torch.nn.modules.conv.LazyConvTranspose2d.html
+++ b/2.9/generated/torch.nn.modules.conv.LazyConvTranspose2d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyConvTranspose2d<a class="headerlink" href="#lazyconvtranspose2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConvTranspose2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1729"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1729"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.ConvTranspose2d.html#torch.nn.ConvTranspose2d" title="torch.nn.ConvTranspose2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.ConvTranspose2d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose2d.html#torch.nn.modules.conv.ConvTranspose2d" title="torch.nn.modules.conv.ConvTranspose2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose2d</span></code></a> is inferred from
 the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4444,7 +4444,7 @@ <h1>LazyConvTranspose2d<a class="headerlink" href="#lazyconvtranspose2d" title="
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConvTranspose2d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L976"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose2d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L976"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose2d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose2d.html#torch.nn.modules.conv.ConvTranspose2d" title="torch.nn.modules.conv.ConvTranspose2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose2d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.conv.LazyConvTranspose3d.html b/2.9/generated/torch.nn.modules.conv.LazyConvTranspose3d.html
index 1f92c153a9b..ab7b251d140 100644
--- a/2.9/generated/torch.nn.modules.conv.LazyConvTranspose3d.html
+++ b/2.9/generated/torch.nn.modules.conv.LazyConvTranspose3d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyConvTranspose3d<a class="headerlink" href="#lazyconvtranspose3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConvTranspose3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1798"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.conv.</span></span><span class="sig-name descname"><span class="pre">LazyConvTranspose3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'zeros'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1798"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.ConvTranspose3d.html#torch.nn.ConvTranspose3d" title="torch.nn.ConvTranspose3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.ConvTranspose3d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">in_channels</span></code> argument of the <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose3d.html#torch.nn.modules.conv.ConvTranspose3d" title="torch.nn.modules.conv.ConvTranspose3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose3d</span></code></a> is inferred from
 the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
@@ -4444,7 +4444,7 @@ <h1>LazyConvTranspose3d<a class="headerlink" href="#lazyconvtranspose3d" title="
 </div>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.conv.LazyConvTranspose3d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/conv.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose3d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/conv.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.conv.LazyConvTranspose3d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.conv.ConvTranspose3d.html#torch.nn.modules.conv.ConvTranspose3d" title="torch.nn.modules.conv.ConvTranspose3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">ConvTranspose3d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.distance.CosineSimilarity.html b/2.9/generated/torch.nn.modules.distance.CosineSimilarity.html
index 30f53ca5de8..8b044bcfab2 100644
--- a/2.9/generated/torch.nn.modules.distance.CosineSimilarity.html
+++ b/2.9/generated/torch.nn.modules.distance.CosineSimilarity.html
@@ -4415,7 +4415,7 @@
 <h1>CosineSimilarity<a class="headerlink" href="#cosinesimilarity" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.distance.CosineSimilarity">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.distance.</span></span><span class="sig-name descname"><span class="pre">CosineSimilarity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/distance.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.distance.CosineSimilarity" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.distance.</span></span><span class="sig-name descname"><span class="pre">CosineSimilarity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/distance.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.distance.CosineSimilarity" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns cosine similarity between <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>1</mn></msub></mrow><annotation encoding="application/x-tex">x_1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>2</mn></msub></mrow><annotation encoding="application/x-tex">x_2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, computed along <cite>dim</cite>.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mtext>similarity</mtext><mo>=</mo><mfrac><mrow><msub><mi>x</mi><mn>1</mn></msub><mo>⋅</mo><msub><mi>x</mi><mn>2</mn></msub></mrow><mrow><mi>max</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi mathvariant="normal">∥</mi><msub><mi>x</mi><mn>1</mn></msub><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub><mo>⋅</mo><mi mathvariant="normal">∥</mi><msub><mi>x</mi><mn>2</mn></msub><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub><mo separator="true">,</mo><mi>ϵ</mi><mo stretchy="false">)</mo></mrow></mfrac><mi mathvariant="normal">.</mi></mrow><annotation encoding="application/x-tex">\text{similarity} = \dfrac{x_1 \cdot x_2}{\max(\Vert x_1 \Vert _2 \cdot \Vert x_2 \Vert _2, \epsilon)}.
@@ -4447,7 +4447,7 @@ <h1>CosineSimilarity<a class="headerlink" href="#cosinesimilarity" title="Permal
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.distance.CosineSimilarity.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/distance.py#L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.distance.CosineSimilarity.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/distance.py#L96"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.distance.CosineSimilarity.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.distance.PairwiseDistance.html b/2.9/generated/torch.nn.modules.distance.PairwiseDistance.html
index 95b8940288e..efc4801942c 100644
--- a/2.9/generated/torch.nn.modules.distance.PairwiseDistance.html
+++ b/2.9/generated/torch.nn.modules.distance.PairwiseDistance.html
@@ -4415,7 +4415,7 @@
 <h1>PairwiseDistance<a class="headerlink" href="#pairwisedistance" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.distance.PairwiseDistance">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.distance.</span></span><span class="sig-name descname"><span class="pre">PairwiseDistance</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/distance.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.distance.PairwiseDistance" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.distance.</span></span><span class="sig-name descname"><span class="pre">PairwiseDistance</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/distance.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.distance.PairwiseDistance" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the pairwise distance between input vectors, or between columns of input matrices.</p>
 <p>Distances are computed using <code class="docutils literal notranslate"><span class="pre">p</span></code>-norm, with constant <code class="docutils literal notranslate"><span class="pre">eps</span></code> added to avoid division by zero
 if <code class="docutils literal notranslate"><span class="pre">p</span></code> is negative, i.e.:</p>
@@ -4455,7 +4455,7 @@ <h1>PairwiseDistance<a class="headerlink" href="#pairwisedistance" title="Permal
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.distance.PairwiseDistance.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/distance.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.distance.PairwiseDistance.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">x2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/distance.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.distance.PairwiseDistance.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.dropout.AlphaDropout.html b/2.9/generated/torch.nn.modules.dropout.AlphaDropout.html
index 494b9cdaf35..6e145664e0b 100644
--- a/2.9/generated/torch.nn.modules.dropout.AlphaDropout.html
+++ b/2.9/generated/torch.nn.modules.dropout.AlphaDropout.html
@@ -4415,7 +4415,7 @@
 <h1>AlphaDropout<a class="headerlink" href="#alphadropout" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.AlphaDropout">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">AlphaDropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.AlphaDropout" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">AlphaDropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.AlphaDropout" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Alpha Dropout over the input.</p>
 <p>Alpha Dropout is a type of Dropout that maintains the self-normalizing
 property.
@@ -4454,7 +4454,7 @@ <h1>AlphaDropout<a class="headerlink" href="#alphadropout" title="Permalink to t
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.AlphaDropout.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.AlphaDropout.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L265"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.AlphaDropout.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.dropout.Dropout.html b/2.9/generated/torch.nn.modules.dropout.Dropout.html
index 09de67253a8..a79c9b4c260 100644
--- a/2.9/generated/torch.nn.modules.dropout.Dropout.html
+++ b/2.9/generated/torch.nn.modules.dropout.Dropout.html
@@ -4415,7 +4415,7 @@
 <h1>Dropout<a class="headerlink" href="#dropout" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.Dropout">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">Dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">Dropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout" title="Permalink to this definition">#</a></dt>
 <dd><p>During training, randomly zeroes some of the elements of the input tensor with probability <code class="xref py py-attr docutils literal notranslate"><span class="pre">p</span></code>.</p>
 <p>The zeroed elements are chosen independently for each forward call and are sampled from a Bernoulli distribution.</p>
 <p>Each channel will be zeroed out independently on every forward call.</p>
@@ -4449,7 +4449,7 @@ <h1>Dropout<a class="headerlink" href="#dropout" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.Dropout.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.dropout.Dropout1d.html b/2.9/generated/torch.nn.modules.dropout.Dropout1d.html
index 1c3fe84596e..3fbecb4e760 100644
--- a/2.9/generated/torch.nn.modules.dropout.Dropout1d.html
+++ b/2.9/generated/torch.nn.modules.dropout.Dropout1d.html
@@ -4415,7 +4415,7 @@
 <h1>Dropout1d<a class="headerlink" href="#dropout1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.Dropout1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">Dropout1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">Dropout1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels.</p>
 <p>A channel is a 1D feature map,
 e.g., the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
@@ -4455,7 +4455,7 @@ <h1>Dropout1d<a class="headerlink" href="#dropout1d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.Dropout1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.dropout.Dropout2d.html b/2.9/generated/torch.nn.modules.dropout.Dropout2d.html
index 8bae992823b..bc0ee29c357 100644
--- a/2.9/generated/torch.nn.modules.dropout.Dropout2d.html
+++ b/2.9/generated/torch.nn.modules.dropout.Dropout2d.html
@@ -4415,7 +4415,7 @@
 <h1>Dropout2d<a class="headerlink" href="#dropout2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.Dropout2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">Dropout2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">Dropout2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels.</p>
 <p>A channel is a 2D feature map,
 e.g., the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
@@ -4463,7 +4463,7 @@ <h1>Dropout2d<a class="headerlink" href="#dropout2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.Dropout2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.dropout.Dropout3d.html b/2.9/generated/torch.nn.modules.dropout.Dropout3d.html
index 07e58c226cd..103e1000416 100644
--- a/2.9/generated/torch.nn.modules.dropout.Dropout3d.html
+++ b/2.9/generated/torch.nn.modules.dropout.Dropout3d.html
@@ -4415,7 +4415,7 @@
 <h1>Dropout3d<a class="headerlink" href="#dropout3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.Dropout3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">Dropout3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">Dropout3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly zero out entire channels.</p>
 <p>A channel is a 3D feature map,
 e.g., the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the
@@ -4455,7 +4455,7 @@ <h1>Dropout3d<a class="headerlink" href="#dropout3d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.Dropout3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L220"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.Dropout3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.dropout.FeatureAlphaDropout.html b/2.9/generated/torch.nn.modules.dropout.FeatureAlphaDropout.html
index ba9da01f3b6..a644ecf5ed0 100644
--- a/2.9/generated/torch.nn.modules.dropout.FeatureAlphaDropout.html
+++ b/2.9/generated/torch.nn.modules.dropout.FeatureAlphaDropout.html
@@ -4415,7 +4415,7 @@
 <h1>FeatureAlphaDropout<a class="headerlink" href="#featurealphadropout" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.FeatureAlphaDropout">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">FeatureAlphaDropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.FeatureAlphaDropout" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.dropout.</span></span><span class="sig-name descname"><span class="pre">FeatureAlphaDropout</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inplace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.FeatureAlphaDropout" title="Permalink to this definition">#</a></dt>
 <dd><p>Randomly masks out entire channels.</p>
 <p>A channel is a feature map,
 e.g. the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>j</mi></mrow><annotation encoding="application/x-tex">j</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.854em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.05724em;">j</span></span></span></span></span>-th channel of the <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>i</mi></mrow><annotation encoding="application/x-tex">i</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6595em;"></span><span class="mord mathnormal">i</span></span></span></span></span>-th sample in the batch input
@@ -4460,7 +4460,7 @@ <h1>FeatureAlphaDropout<a class="headerlink" href="#featurealphadropout" title="
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.dropout.FeatureAlphaDropout.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/dropout.py#L319"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.FeatureAlphaDropout.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/dropout.py#L319"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.dropout.FeatureAlphaDropout.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.flatten.Flatten.html b/2.9/generated/torch.nn.modules.flatten.Flatten.html
index d5fc610c31f..fe8cd1bbcda 100644
--- a/2.9/generated/torch.nn.modules.flatten.Flatten.html
+++ b/2.9/generated/torch.nn.modules.flatten.Flatten.html
@@ -4404,7 +4404,7 @@
 <h1>Flatten<a class="headerlink" href="#flatten" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.flatten.Flatten">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.flatten.</span></span><span class="sig-name descname"><span class="pre">Flatten</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">start_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/flatten.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Flatten" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.flatten.</span></span><span class="sig-name descname"><span class="pre">Flatten</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">start_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/flatten.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Flatten" title="Permalink to this definition">#</a></dt>
 <dd><p>Flattens a contiguous range of dims into a tensor.</p>
 <p>For use with <code class="xref py py-class docutils literal notranslate"><span class="pre">Sequential</span></code>, see <a class="reference internal" href="torch.flatten.html#torch.flatten" title="torch.flatten"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.flatten()</span></code></a> for details.</p>
 <dl class="simple">
@@ -4442,7 +4442,7 @@ <h1>Flatten<a class="headerlink" href="#flatten" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.flatten.Flatten.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/flatten.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Flatten.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/flatten.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Flatten.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4453,7 +4453,7 @@ <h1>Flatten<a class="headerlink" href="#flatten" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.flatten.Flatten.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/flatten.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Flatten.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/flatten.py#L52"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Flatten.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.flatten.Unflatten.html b/2.9/generated/torch.nn.modules.flatten.Unflatten.html
index c860daba3d4..d8aa9992aaf 100644
--- a/2.9/generated/torch.nn.modules.flatten.Unflatten.html
+++ b/2.9/generated/torch.nn.modules.flatten.Unflatten.html
@@ -4404,7 +4404,7 @@
 <h1>Unflatten<a class="headerlink" href="#unflatten" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.flatten.Unflatten">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.flatten.</span></span><span class="sig-name descname"><span class="pre">Unflatten</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unflattened_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/flatten.py#L65"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Unflatten" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.flatten.</span></span><span class="sig-name descname"><span class="pre">Unflatten</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unflattened_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/flatten.py#L65"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Unflatten" title="Permalink to this definition">#</a></dt>
 <dd><p>Unflattens a tensor dim expanding it to a desired shape. For use with <code class="xref py py-class docutils literal notranslate"><span class="pre">Sequential</span></code>.</p>
 <ul class="simple">
 <li><p><code class="xref py py-attr docutils literal notranslate"><span class="pre">dim</span></code> specifies the dimension of the input tensor to be unflattened, and it can
@@ -4464,7 +4464,7 @@ <h1>Unflatten<a class="headerlink" href="#unflatten" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.flatten.Unflatten.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/flatten.py#L166"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Unflatten.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/flatten.py#L166"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Unflatten.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4475,7 +4475,7 @@ <h1>Unflatten<a class="headerlink" href="#unflatten" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.flatten.Unflatten.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/flatten.py#L160"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Unflatten.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/flatten.py#L160"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.flatten.Unflatten.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.fold.Fold.html b/2.9/generated/torch.nn.modules.fold.Fold.html
index ee6ff7dd623..78d9ca3ae3d 100644
--- a/2.9/generated/torch.nn.modules.fold.Fold.html
+++ b/2.9/generated/torch.nn.modules.fold.Fold.html
@@ -4415,7 +4415,7 @@
 <h1>Fold<a class="headerlink" href="#fold" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.fold.Fold">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.fold.</span></span><span class="sig-name descname"><span class="pre">Fold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Fold" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.fold.</span></span><span class="sig-name descname"><span class="pre">Fold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Fold" title="Permalink to this definition">#</a></dt>
 <dd><p>Combines an array of sliding local blocks into a large containing tensor.</p>
 <p>Consider a batched <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> tensor containing sliding local blocks,
 e.g., patches of images, of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo>×</mo><mo>∏</mo><mo stretchy="false">(</mo><mtext>kernel_size</mtext><mo stretchy="false">)</mo><mo separator="true">,</mo><mi>L</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C \times  \prod(\text{kernel\_size}), L)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1.06em;vertical-align:-0.31em;"></span><span class="mop op-symbol small-op" style="position:relative;top:0em;">∏</span><span class="mopen">(</span><span class="mord text"><span class="mord">kernel_size</span></span><span class="mclose">)</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">L</span><span class="mclose">)</span></span></span></span></span>,
@@ -4525,7 +4525,7 @@ <h1>Fold<a class="headerlink" href="#fold" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.fold.Fold.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Fold.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Fold.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4536,7 +4536,7 @@ <h1>Fold<a class="headerlink" href="#fold" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.fold.Fold.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Fold.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Fold.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.fold.Unfold.html b/2.9/generated/torch.nn.modules.fold.Unfold.html
index 706d1ac346c..10dce143553 100644
--- a/2.9/generated/torch.nn.modules.fold.Unfold.html
+++ b/2.9/generated/torch.nn.modules.fold.Unfold.html
@@ -4415,7 +4415,7 @@
 <h1>Unfold<a class="headerlink" href="#unfold" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.fold.Unfold">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.fold.</span></span><span class="sig-name descname"><span class="pre">Unfold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Unfold" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.fold.</span></span><span class="sig-name descname"><span class="pre">Unfold</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L174"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Unfold" title="Permalink to this definition">#</a></dt>
 <dd><p>Extracts sliding local blocks from a batched input tensor.</p>
 <p>Consider a batched <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mo>∗</mo><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, *)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">∗</span><span class="mclose">)</span></span></span></span></span>,
 where <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>N</mi></mrow><annotation encoding="application/x-tex">N</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span></span></span></span></span> is the batch dimension, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>C</mi></mrow><annotation encoding="application/x-tex">C</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span></span></span></span></span> is the channel dimension,
@@ -4533,7 +4533,7 @@ <h1>Unfold<a class="headerlink" href="#unfold" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.fold.Unfold.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L328"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Unfold.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L328"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Unfold.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4544,7 +4544,7 @@ <h1>Unfold<a class="headerlink" href="#unfold" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.fold.Unfold.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/fold.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Unfold.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/fold.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.fold.Unfold.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm1d.html b/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm1d.html
index 2e5a1977187..45b731b4a3d 100644
--- a/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm1d.html
+++ b/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm1d.html
@@ -4415,7 +4415,7 @@
 <h1>InstanceNorm1d<a class="headerlink" href="#instancenorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.InstanceNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.InstanceNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.InstanceNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Instance Normalization.</p>
 <p>This operation applies Instance Normalization
 over a 2D (unbatched) or 3D (batched) input as described in the paper
diff --git a/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm2d.html b/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm2d.html
index 554be72fd8e..a8e7dde9d3a 100644
--- a/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm2d.html
+++ b/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm2d.html
@@ -4415,7 +4415,7 @@
 <h1>InstanceNorm2d<a class="headerlink" href="#instancenorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.InstanceNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.InstanceNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.InstanceNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Instance Normalization.</p>
 <p>This operation applies Instance Normalization
 over a 4D input (a mini-batch of 2D inputs
diff --git a/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm3d.html b/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm3d.html
index 57113c94b14..4c6c0fbb98d 100644
--- a/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm3d.html
+++ b/2.9/generated/torch.nn.modules.instancenorm.InstanceNorm3d.html
@@ -4415,7 +4415,7 @@
 <h1>InstanceNorm3d<a class="headerlink" href="#instancenorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.InstanceNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.InstanceNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">InstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.InstanceNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Instance Normalization.</p>
 <p>This operation applies Instance Normalization
 over a 5D input (a mini-batch of 3D inputs with additional channel dimension) as described in the paper
diff --git a/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm1d.html b/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm1d.html
index 2802617bdfb..10ebd22d97d 100644
--- a/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm1d.html
+++ b/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm1d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyInstanceNorm1d<a class="headerlink" href="#lazyinstancenorm1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.LazyInstanceNorm1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm1d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.InstanceNorm1d.html#torch.nn.InstanceNorm1d" title="torch.nn.InstanceNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.InstanceNorm1d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm1d.html#torch.nn.modules.instancenorm.InstanceNorm1d" title="torch.nn.modules.instancenorm.InstanceNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm1d</span></code></a> is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite>, <cite>bias</cite>, <cite>running_mean</cite> and <cite>running_var</cite>.</p>
@@ -4447,7 +4447,7 @@ <h1>LazyInstanceNorm1d<a class="headerlink" href="#lazyinstancenorm1d" title="Pe
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.LazyInstanceNorm1d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm1d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm1d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm1d.html#torch.nn.modules.instancenorm.InstanceNorm1d" title="torch.nn.modules.instancenorm.InstanceNorm1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm1d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm2d.html b/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm2d.html
index 34daff8cf30..60339d5e796 100644
--- a/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm2d.html
+++ b/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm2d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyInstanceNorm2d<a class="headerlink" href="#lazyinstancenorm2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.LazyInstanceNorm2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm2d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.InstanceNorm2d.html#torch.nn.InstanceNorm2d" title="torch.nn.InstanceNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.InstanceNorm2d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm2d.html#torch.nn.modules.instancenorm.InstanceNorm2d" title="torch.nn.modules.instancenorm.InstanceNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm2d</span></code></a> is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite>, <cite>bias</cite>,
@@ -4448,7 +4448,7 @@ <h1>LazyInstanceNorm2d<a class="headerlink" href="#lazyinstancenorm2d" title="Pe
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.LazyInstanceNorm2d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm2d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm2d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm2d.html#torch.nn.modules.instancenorm.InstanceNorm2d" title="torch.nn.modules.instancenorm.InstanceNorm2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm2d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm3d.html b/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm3d.html
index 83e0b533494..eec3b3f2cdc 100644
--- a/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm3d.html
+++ b/2.9/generated/torch.nn.modules.instancenorm.LazyInstanceNorm3d.html
@@ -4415,7 +4415,7 @@
 <h1>LazyInstanceNorm3d<a class="headerlink" href="#lazyinstancenorm3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.LazyInstanceNorm3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.instancenorm.</span></span><span class="sig-name descname"><span class="pre">LazyInstanceNorm3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">track_running_stats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm3d" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.InstanceNorm3d.html#torch.nn.InstanceNorm3d" title="torch.nn.InstanceNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.InstanceNorm3d</span></code></a> module with lazy initialization of the <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument.</p>
 <p>The <code class="docutils literal notranslate"><span class="pre">num_features</span></code> argument of the <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm3d.html#torch.nn.modules.instancenorm.InstanceNorm3d" title="torch.nn.modules.instancenorm.InstanceNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm3d</span></code></a> is inferred from the <code class="docutils literal notranslate"><span class="pre">input.size(1)</span></code>.
 The attributes that will be lazily initialized are <cite>weight</cite>, <cite>bias</cite>,
@@ -4448,7 +4448,7 @@ <h1>LazyInstanceNorm3d<a class="headerlink" href="#lazyinstancenorm3d" title="Pe
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.instancenorm.LazyInstanceNorm3d.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/instancenorm.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm3d.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/instancenorm.py#L358"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.instancenorm.LazyInstanceNorm3d.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.instancenorm.InstanceNorm3d.html#torch.nn.modules.instancenorm.InstanceNorm3d" title="torch.nn.modules.instancenorm.InstanceNorm3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">InstanceNorm3d</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.modules.lazy.LazyModuleMixin.html b/2.9/generated/torch.nn.modules.lazy.LazyModuleMixin.html
index 89417416cc5..dd5aa7cec4c 100644
--- a/2.9/generated/torch.nn.modules.lazy.LazyModuleMixin.html
+++ b/2.9/generated/torch.nn.modules.lazy.LazyModuleMixin.html
@@ -4404,7 +4404,7 @@
 <h1>LazyModuleMixin<a class="headerlink" href="#lazymodulemixin" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.lazy.LazyModuleMixin">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.lazy.</span></span><span class="sig-name descname"><span class="pre">LazyModuleMixin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/lazy.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.lazy.LazyModuleMixin" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.lazy.</span></span><span class="sig-name descname"><span class="pre">LazyModuleMixin</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/lazy.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.lazy.LazyModuleMixin" title="Permalink to this definition">#</a></dt>
 <dd><p>A mixin for modules that lazily initialize parameters, also known as “lazy modules”.</p>
 <p>Modules that lazily initialize parameters, or “lazy modules”,
 derive the shapes of their parameters from the first input(s)
@@ -4510,7 +4510,7 @@ <h1>LazyModuleMixin<a class="headerlink" href="#lazymodulemixin" title="Permalin
 when the state is loaded. This prevents using initialized modules in different contexts.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.lazy.LazyModuleMixin.has_uninitialized_params">
-<span class="sig-name descname"><span class="pre">has_uninitialized_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/lazy.py#L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.lazy.LazyModuleMixin.has_uninitialized_params" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">has_uninitialized_params</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/lazy.py#L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.lazy.LazyModuleMixin.has_uninitialized_params" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if a module has parameters that are not initialized.</p>
 <dl class="field-list simple">
 </dl>
@@ -4518,7 +4518,7 @@ <h1>LazyModuleMixin<a class="headerlink" href="#lazymodulemixin" title="Permalin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.lazy.LazyModuleMixin.initialize_parameters">
-<span class="sig-name descname"><span class="pre">initialize_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/lazy.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.lazy.LazyModuleMixin.initialize_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">initialize_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/lazy.py#L227"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.lazy.LazyModuleMixin.initialize_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize parameters according to the input batch properties.</p>
 <p>This adds an interface to isolate parameter initialization from the
 forward pass when doing parameter shape inference.</p>
diff --git a/2.9/generated/torch.nn.modules.linear.Bilinear.html b/2.9/generated/torch.nn.modules.linear.Bilinear.html
index dfda6e9f4e1..81936525a5a 100644
--- a/2.9/generated/torch.nn.modules.linear.Bilinear.html
+++ b/2.9/generated/torch.nn.modules.linear.Bilinear.html
@@ -4415,7 +4415,7 @@
 <h1>Bilinear<a class="headerlink" href="#bilinear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Bilinear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.linear.</span></span><span class="sig-name descname"><span class="pre">Bilinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in1_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in2_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Bilinear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.linear.</span></span><span class="sig-name descname"><span class="pre">Bilinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in1_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in2_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Bilinear" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a bilinear transformation to the incoming data: <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><msubsup><mi>x</mi><mn>1</mn><mi>T</mi></msubsup><mi>A</mi><msub><mi>x</mi><mn>2</mn></msub><mo>+</mo><mi>b</mi></mrow><annotation encoding="application/x-tex">y = x_1^T A x_2 + b</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.0894em;vertical-align:-0.2481em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8413em;"><span style="top:-2.4519em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight" style="margin-right:0.13889em;">T</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2481em;"><span></span></span></span></span></span></span><span class="mord mathnormal">A</span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal">b</span></span></span></span></span>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4508,7 +4508,7 @@ <h1>Bilinear<a class="headerlink" href="#bilinear" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Bilinear.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L247"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Bilinear.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L247"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Bilinear.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4519,7 +4519,7 @@ <h1>Bilinear<a class="headerlink" href="#bilinear" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Bilinear.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Bilinear.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Bilinear.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4530,7 +4530,7 @@ <h1>Bilinear<a class="headerlink" href="#bilinear" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Bilinear.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L232"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Bilinear.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L232"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Bilinear.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.linear.Identity.html b/2.9/generated/torch.nn.modules.linear.Identity.html
index c55b58b6d98..05291807054 100644
--- a/2.9/generated/torch.nn.modules.linear.Identity.html
+++ b/2.9/generated/torch.nn.modules.linear.Identity.html
@@ -4415,7 +4415,7 @@
 <h1>Identity<a class="headerlink" href="#identity" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Identity">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.linear.</span></span><span class="sig-name descname"><span class="pre">Identity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Identity" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.linear.</span></span><span class="sig-name descname"><span class="pre">Identity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Identity" title="Permalink to this definition">#</a></dt>
 <dd><p>A placeholder identity operator that is argument-insensitive.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4442,7 +4442,7 @@ <h1>Identity<a class="headerlink" href="#identity" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Identity.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Identity.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Identity.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.linear.LazyLinear.html b/2.9/generated/torch.nn.modules.linear.LazyLinear.html
index d30338f3f8a..3915c88566d 100644
--- a/2.9/generated/torch.nn.modules.linear.LazyLinear.html
+++ b/2.9/generated/torch.nn.modules.linear.LazyLinear.html
@@ -4415,7 +4415,7 @@
 <h1>LazyLinear<a class="headerlink" href="#lazylinear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.LazyLinear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.linear.</span></span><span class="sig-name descname"><span class="pre">LazyLinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.LazyLinear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.linear.</span></span><span class="sig-name descname"><span class="pre">LazyLinear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.LazyLinear" title="Permalink to this definition">#</a></dt>
 <dd><p>A <a class="reference internal" href="torch.nn.Linear.html#torch.nn.Linear" title="torch.nn.Linear"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Linear</span></code></a> module where <cite>in_features</cite> is inferred.</p>
 <p>In this module, the <cite>weight</cite> and <cite>bias</cite> are of <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.UninitializedParameter</span></code>
 class. They will be initialized after the first call to <code class="docutils literal notranslate"><span class="pre">forward</span></code> is done and the
@@ -4490,13 +4490,13 @@ <h1>LazyLinear<a class="headerlink" href="#lazylinear" title="Permalink to this
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.LazyLinear.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.LazyLinear.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.LazyLinear.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.modules.linear.Linear.html#torch.nn.modules.linear.Linear" title="torch.nn.modules.linear.Linear"><code class="xref py py-class docutils literal notranslate"><span class="pre">Linear</span></code></a></p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.LazyLinear.initialize_parameters">
-<span class="sig-name descname"><span class="pre">initialize_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.LazyLinear.initialize_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">initialize_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.LazyLinear.initialize_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Infers <code class="docutils literal notranslate"><span class="pre">in_features</span></code> based on <code class="docutils literal notranslate"><span class="pre">input</span></code> and initializes parameters.</p>
 <dl class="field-list simple">
 </dl>
@@ -4504,7 +4504,7 @@ <h1>LazyLinear<a class="headerlink" href="#lazylinear" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.LazyLinear.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.LazyLinear.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L302"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.LazyLinear.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.linear.Linear.html b/2.9/generated/torch.nn.modules.linear.Linear.html
index 0c20e6d7b6f..9884577c1ad 100644
--- a/2.9/generated/torch.nn.modules.linear.Linear.html
+++ b/2.9/generated/torch.nn.modules.linear.Linear.html
@@ -4415,7 +4415,7 @@
 <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Linear">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.linear.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Linear" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.linear.</span></span><span class="sig-name descname"><span class="pre">Linear</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">in_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_features</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Linear" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies an affine linear transformation to the incoming data: <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mi>x</mi><msup><mi>A</mi><mi>T</mi></msup><mo>+</mo><mi>b</mi></mrow><annotation encoding="application/x-tex">y = xA^T + b</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.9247em;vertical-align:-0.0833em;"></span><span class="mord mathnormal">x</span><span class="mord"><span class="mord mathnormal">A</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8413em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight" style="margin-right:0.13889em;">T</span></span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal">b</span></span></span></span></span>.</p>
 <p>This module supports <a class="reference internal" href="../notes/cuda.html#tf32-on-ampere"><span class="std std-ref">TensorFloat32</span></a>.</p>
 <p>On certain ROCm devices, when using float16 inputs this module will use <a class="reference internal" href="../notes/numerical_accuracy.html#fp16-on-mi200"><span class="std std-ref">different precision</span></a> for backward.</p>
@@ -4506,7 +4506,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Linear.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Linear.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Linear.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4517,7 +4517,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Linear.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Linear.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Linear.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4528,7 +4528,7 @@ <h1>Linear<a class="headerlink" href="#linear" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.linear.Linear.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/linear.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Linear.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/linear.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.linear.Linear.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in <code class="docutils literal notranslate"><span class="pre">__init__</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.loss.BCELoss.html b/2.9/generated/torch.nn.modules.loss.BCELoss.html
index a394481d171..ee4ccb37c0e 100644
--- a/2.9/generated/torch.nn.modules.loss.BCELoss.html
+++ b/2.9/generated/torch.nn.modules.loss.BCELoss.html
@@ -4415,7 +4415,7 @@
 <h1>BCELoss<a class="headerlink" href="#bceloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.BCELoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">BCELoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L637"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.BCELoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">BCELoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L637"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.BCELoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the Binary Cross Entropy between the target and
 the input probabilities:</p>
 <p>The unreduced (i.e. with <code class="xref py py-attr docutils literal notranslate"><span class="pre">reduction</span></code> set to <code class="docutils literal notranslate"><span class="pre">'none'</span></code>) loss can be described as:</p>
@@ -4490,7 +4490,7 @@ <h1>BCELoss<a class="headerlink" href="#bceloss" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.BCELoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L723"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.BCELoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L723"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.BCELoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.BCEWithLogitsLoss.html b/2.9/generated/torch.nn.modules.loss.BCEWithLogitsLoss.html
index efd791e29ae..4b1ba72e261 100644
--- a/2.9/generated/torch.nn.modules.loss.BCEWithLogitsLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.BCEWithLogitsLoss.html
@@ -4415,7 +4415,7 @@
 <h1>BCEWithLogitsLoss<a class="headerlink" href="#bcewithlogitsloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.BCEWithLogitsLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">BCEWithLogitsLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.BCEWithLogitsLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">BCEWithLogitsLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pos_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L732"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.BCEWithLogitsLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>This loss combines a <cite>Sigmoid</cite> layer and the <cite>BCELoss</cite> in one single
 class. This version is more numerically stable than using a plain <cite>Sigmoid</cite>
 followed by a <cite>BCELoss</cite> as, by combining the operations into one layer,
@@ -4516,7 +4516,7 @@ <h1>BCEWithLogitsLoss<a class="headerlink" href="#bcewithlogitsloss" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.BCEWithLogitsLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L848"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.BCEWithLogitsLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L848"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.BCEWithLogitsLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.CTCLoss.html b/2.9/generated/torch.nn.modules.loss.CTCLoss.html
index cdd03a7188e..05065b4ff97 100644
--- a/2.9/generated/torch.nn.modules.loss.CTCLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.CTCLoss.html
@@ -4415,7 +4415,7 @@
 <h1>CTCLoss<a class="headerlink" href="#ctcloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.CTCLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">CTCLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">blank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_infinity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1932"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CTCLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">CTCLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">blank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">zero_infinity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1932"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CTCLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>The Connectionist Temporal Classification loss.</p>
 <p>Calculates loss between a continuous (unsegmented) time series and a target sequence. CTCLoss sums over the
 probability of possible alignments of input to target, producing a loss value which is differentiable
@@ -4570,7 +4570,7 @@ <h1>CTCLoss<a class="headerlink" href="#ctcloss" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.CTCLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_probs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">targets</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_lengths</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L2093"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CTCLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_probs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">targets</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target_lengths</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L2093"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CTCLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.CosineEmbeddingLoss.html b/2.9/generated/torch.nn.modules.loss.CosineEmbeddingLoss.html
index b1ae4f8e5f4..2198bb1ddfe 100644
--- a/2.9/generated/torch.nn.modules.loss.CosineEmbeddingLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.CosineEmbeddingLoss.html
@@ -4415,7 +4415,7 @@
 <h1>CosineEmbeddingLoss<a class="headerlink" href="#cosineembeddingloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.CosineEmbeddingLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">CosineEmbeddingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CosineEmbeddingLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">CosineEmbeddingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CosineEmbeddingLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the loss given input tensors
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>1</mn></msub></mrow><annotation encoding="application/x-tex">x_1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>x</mi><mn>2</mn></msub></mrow><annotation encoding="application/x-tex">x_2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.5806em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">x</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3011em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> and a <cite>Tensor</cite> label <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> with values 1 or -1.
 Use (<span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mn>1</mn></mrow><annotation encoding="application/x-tex">y=1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord">1</span></span></span></span></span>) to maximize the cosine similarity of two inputs, and (<span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi><mo>=</mo><mo>−</mo><mn>1</mn></mrow><annotation encoding="application/x-tex">y=-1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.7278em;vertical-align:-0.0833em;"></span><span class="mord">−</span><span class="mord">1</span></span></span></span></span>) otherwise.
@@ -4473,7 +4473,7 @@ <h1>CosineEmbeddingLoss<a class="headerlink" href="#cosineembeddingloss" title="
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.CosineEmbeddingLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1517"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CosineEmbeddingLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1517"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CosineEmbeddingLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.CrossEntropyLoss.html b/2.9/generated/torch.nn.modules.loss.CrossEntropyLoss.html
index d9da0391155..77e18b96bd7 100644
--- a/2.9/generated/torch.nn.modules.loss.CrossEntropyLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.CrossEntropyLoss.html
@@ -4415,7 +4415,7 @@
 <h1>CrossEntropyLoss<a class="headerlink" href="#crossentropyloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.CrossEntropyLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">CrossEntropyLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label_smoothing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CrossEntropyLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">CrossEntropyLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label_smoothing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CrossEntropyLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>This criterion computes the cross entropy loss between input logits
 and target.</p>
 <p>It is useful when training a classification problem with <cite>C</cite> classes.
@@ -4598,7 +4598,7 @@ <h1>CrossEntropyLoss<a class="headerlink" href="#crossentropyloss" title="Permal
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.CrossEntropyLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CrossEntropyLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.CrossEntropyLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.GaussianNLLLoss.html b/2.9/generated/torch.nn.modules.loss.GaussianNLLLoss.html
index e3f9b70bcbd..2a3ab738282 100644
--- a/2.9/generated/torch.nn.modules.loss.GaussianNLLLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.GaussianNLLLoss.html
@@ -4415,7 +4415,7 @@
 <h1>GaussianNLLLoss<a class="headerlink" href="#gaussiannllloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.GaussianNLLLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">GaussianNLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L376"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.GaussianNLLLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">GaussianNLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L376"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.GaussianNLLLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Gaussian negative log likelihood loss.</p>
 <p>The targets are treated as samples from Gaussian distributions with
 expectations and variances predicted by the neural network. For a
@@ -4491,7 +4491,7 @@ <h1>GaussianNLLLoss<a class="headerlink" href="#gaussiannllloss" title="Permalin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.GaussianNLLLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">var</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.GaussianNLLLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">var</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L454"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.GaussianNLLLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.HingeEmbeddingLoss.html b/2.9/generated/torch.nn.modules.loss.HingeEmbeddingLoss.html
index 1ffb193d15f..db89a16488b 100644
--- a/2.9/generated/torch.nn.modules.loss.HingeEmbeddingLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.HingeEmbeddingLoss.html
@@ -4415,7 +4415,7 @@
 <h1>HingeEmbeddingLoss<a class="headerlink" href="#hingeembeddingloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.HingeEmbeddingLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">HingeEmbeddingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L859"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.HingeEmbeddingLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">HingeEmbeddingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L859"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.HingeEmbeddingLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Measures the loss given an input tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and a labels tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span>
 (containing 1 or -1).
 This is usually used for measuring whether two inputs are similar or
@@ -4469,7 +4469,7 @@ <h1>HingeEmbeddingLoss<a class="headerlink" href="#hingeembeddingloss" title="Pe
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.HingeEmbeddingLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L922"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.HingeEmbeddingLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L922"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.HingeEmbeddingLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.HuberLoss.html b/2.9/generated/torch.nn.modules.loss.HuberLoss.html
index 0b8abc9cb71..edf5681c33a 100644
--- a/2.9/generated/torch.nn.modules.loss.HuberLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.HuberLoss.html
@@ -4415,7 +4415,7 @@
 <h1>HuberLoss<a class="headerlink" href="#huberloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.HuberLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">HuberLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1080"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.HuberLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">HuberLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1080"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.HuberLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that uses a squared term if the absolute
 element-wise error falls below delta and a delta-scaled L1 term otherwise.
 This loss combines advantages of both <a class="reference internal" href="torch.nn.modules.loss.L1Loss.html#torch.nn.modules.loss.L1Loss" title="torch.nn.modules.loss.L1Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">L1Loss</span></code></a> and <a class="reference internal" href="torch.nn.modules.loss.MSELoss.html#torch.nn.modules.loss.MSELoss" title="torch.nn.modules.loss.MSELoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">MSELoss</span></code></a>; the
@@ -4471,7 +4471,7 @@ <h1>HuberLoss<a class="headerlink" href="#huberloss" title="Permalink to this he
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.HuberLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.HuberLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.HuberLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.KLDivLoss.html b/2.9/generated/torch.nn.modules.loss.KLDivLoss.html
index 7512b4a3e68..69fd70ab13d 100644
--- a/2.9/generated/torch.nn.modules.loss.KLDivLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.KLDivLoss.html
@@ -4415,7 +4415,7 @@
 <h1>KLDivLoss<a class="headerlink" href="#kldivloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.KLDivLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">KLDivLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L465"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.KLDivLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">KLDivLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">log_target</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L465"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.KLDivLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>The Kullback-Leibler divergence loss.</p>
 <p>For tensors of the same shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>y</mi><mtext>pred</mtext></msub><mo separator="true">,</mo><mtext> </mtext><msub><mi>y</mi><mtext>true</mtext></msub></mrow><annotation encoding="application/x-tex">y_{\text{pred}},\ y_{\text{true}}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7167em;vertical-align:-0.2861em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">pred</span></span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2861em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace"> </span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">true</span></span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>,
 where <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>y</mi><mtext>pred</mtext></msub></mrow><annotation encoding="application/x-tex">y_{\text{pred}}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7167em;vertical-align:-0.2861em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">pred</span></span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.2861em;"><span></span></span></span></span></span></span></span></span></span></span> is the <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>y</mi><mtext>true</mtext></msub></mrow><annotation encoding="application/x-tex">y_{\text{true}}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">true</span></span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> is the
@@ -4498,7 +4498,7 @@ <h1>KLDivLoss<a class="headerlink" href="#kldivloss" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.KLDivLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.KLDivLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.KLDivLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.L1Loss.html b/2.9/generated/torch.nn.modules.loss.L1Loss.html
index 41623c230e6..da071862b8f 100644
--- a/2.9/generated/torch.nn.modules.loss.L1Loss.html
+++ b/2.9/generated/torch.nn.modules.loss.L1Loss.html
@@ -4415,7 +4415,7 @@
 <h1>L1Loss<a class="headerlink" href="#l1loss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.L1Loss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">L1Loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.L1Loss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">L1Loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.L1Loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the mean absolute error (MAE) between each element in
 the input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and target <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span>.</p>
 <p>The unreduced (i.e. with <code class="xref py py-attr docutils literal notranslate"><span class="pre">reduction</span></code> set to <code class="docutils literal notranslate"><span class="pre">'none'</span></code>) loss can be described as:</p>
@@ -4477,7 +4477,7 @@ <h1>L1Loss<a class="headerlink" href="#l1loss" title="Permalink to this heading"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.L1Loss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.L1Loss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L128"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.L1Loss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.MSELoss.html b/2.9/generated/torch.nn.modules.loss.MSELoss.html
index cf9cf1238da..47bff4bf7e1 100644
--- a/2.9/generated/torch.nn.modules.loss.MSELoss.html
+++ b/2.9/generated/torch.nn.modules.loss.MSELoss.html
@@ -4415,7 +4415,7 @@
 <h1>MSELoss<a class="headerlink" href="#mseloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MSELoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MSELoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L568"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MSELoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MSELoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L568"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MSELoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the mean squared error (squared L2 norm) between
 each element in the input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and target <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span>.</p>
 <p>The unreduced (i.e. with <code class="xref py py-attr docutils literal notranslate"><span class="pre">reduction</span></code> set to <code class="docutils literal notranslate"><span class="pre">'none'</span></code>) loss can be described as:</p>
@@ -4474,7 +4474,7 @@ <h1>MSELoss<a class="headerlink" href="#mseloss" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MSELoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L630"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MSELoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L630"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MSELoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.MarginRankingLoss.html b/2.9/generated/torch.nn.modules.loss.MarginRankingLoss.html
index ed242a96850..4e1b7958083 100644
--- a/2.9/generated/torch.nn.modules.loss.MarginRankingLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.MarginRankingLoss.html
@@ -4415,7 +4415,7 @@
 <h1>MarginRankingLoss<a class="headerlink" href="#marginrankingloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MarginRankingLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MarginRankingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1524"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MarginRankingLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MarginRankingLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1524"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MarginRankingLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the loss given
 inputs <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>1</mn></mrow><annotation encoding="application/x-tex">x1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">1</span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>2</mn></mrow><annotation encoding="application/x-tex">x2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">2</span></span></span></span></span>, two 1D mini-batch or 0D <cite>Tensors</cite>,
 and a label 1D mini-batch or 0D <cite>Tensor</cite> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> (containing 1 or -1).</p>
@@ -4467,7 +4467,7 @@ <h1>MarginRankingLoss<a class="headerlink" href="#marginrankingloss" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MarginRankingLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1584"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MarginRankingLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1584"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MarginRankingLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.MultiLabelMarginLoss.html b/2.9/generated/torch.nn.modules.loss.MultiLabelMarginLoss.html
index f26b390a424..7a011799db4 100644
--- a/2.9/generated/torch.nn.modules.loss.MultiLabelMarginLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.MultiLabelMarginLoss.html
@@ -4415,7 +4415,7 @@
 <h1>MultiLabelMarginLoss<a class="headerlink" href="#multilabelmarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MultiLabelMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MultiLabelMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L929"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiLabelMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MultiLabelMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L929"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiLabelMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that optimizes a multi-class multi-classification
 hinge loss (margin-based loss) between input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> (a 2D mini-batch <cite>Tensor</cite>)
 and output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> (which is a 2D <cite>Tensor</cite> of target class indices).
@@ -4470,7 +4470,7 @@ <h1>MultiLabelMarginLoss<a class="headerlink" href="#multilabelmarginloss" title
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MultiLabelMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L990"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiLabelMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L990"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiLabelMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.MultiLabelSoftMarginLoss.html b/2.9/generated/torch.nn.modules.loss.MultiLabelSoftMarginLoss.html
index 63988ae23cf..2e1beb346ba 100644
--- a/2.9/generated/torch.nn.modules.loss.MultiLabelSoftMarginLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.MultiLabelSoftMarginLoss.html
@@ -4415,7 +4415,7 @@
 <h1>MultiLabelSoftMarginLoss<a class="headerlink" href="#multilabelsoftmarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MultiLabelSoftMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MultiLabelSoftMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiLabelSoftMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MultiLabelSoftMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiLabelSoftMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that optimizes a multi-label one-versus-all
 loss based on max-entropy, between input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and target <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> of size
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mclose">)</span></span></span></span></span>.
@@ -4460,7 +4460,7 @@ <h1>MultiLabelSoftMarginLoss<a class="headerlink" href="#multilabelsoftmarginlos
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MultiLabelSoftMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1445"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiLabelSoftMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1445"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiLabelSoftMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.MultiMarginLoss.html b/2.9/generated/torch.nn.modules.loss.MultiMarginLoss.html
index b82725baee5..ed1d61529bb 100644
--- a/2.9/generated/torch.nn.modules.loss.MultiMarginLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.MultiMarginLoss.html
@@ -4415,7 +4415,7 @@
 <h1>MultiMarginLoss<a class="headerlink" href="#multimarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MultiMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MultiMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1591"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">MultiMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1591"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that optimizes a multi-class classification hinge
 loss (margin-based loss) between input <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> (a 2D mini-batch <cite>Tensor</cite>) and
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span> (which is a 1D tensor of target class indices,
@@ -4479,7 +4479,7 @@ <h1>MultiMarginLoss<a class="headerlink" href="#multimarginloss" title="Permalin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.MultiMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.MultiMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.NLLLoss.html b/2.9/generated/torch.nn.modules.loss.NLLLoss.html
index 94ad623876c..b957f6d307b 100644
--- a/2.9/generated/torch.nn.modules.loss.NLLLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.NLLLoss.html
@@ -4415,7 +4415,7 @@
 <h1>NLLLoss<a class="headerlink" href="#nllloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.NLLLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">NLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L135"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.NLLLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">NLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ignore_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L135"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.NLLLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>The negative log likelihood loss. It is useful to train a classification
 problem with <cite>C</cite> classes.</p>
 <p>If provided, the optional argument <code class="xref py py-attr docutils literal notranslate"><span class="pre">weight</span></code> should be a 1D Tensor assigning
@@ -4522,7 +4522,7 @@ <h1>NLLLoss<a class="headerlink" href="#nllloss" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.NLLLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L255"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.NLLLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L255"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.NLLLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.PoissonNLLLoss.html b/2.9/generated/torch.nn.modules.loss.PoissonNLLLoss.html
index 5c056893569..753b6c90c27 100644
--- a/2.9/generated/torch.nn.modules.loss.PoissonNLLLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.PoissonNLLLoss.html
@@ -4415,7 +4415,7 @@
 <h1>PoissonNLLLoss<a class="headerlink" href="#poissonnllloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.PoissonNLLLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">PoissonNLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.PoissonNLLLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">PoissonNLLLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_input</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.PoissonNLLLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Negative log likelihood loss with Poisson distribution of target.</p>
 <p>The loss can be described as:</p>
 <div class="math">
@@ -4476,7 +4476,7 @@ <h1>PoissonNLLLoss<a class="headerlink" href="#poissonnllloss" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.PoissonNLLLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.PoissonNLLLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.PoissonNLLLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.SmoothL1Loss.html b/2.9/generated/torch.nn.modules.loss.SmoothL1Loss.html
index f6d048531d0..66c45d749f9 100644
--- a/2.9/generated/torch.nn.modules.loss.SmoothL1Loss.html
+++ b/2.9/generated/torch.nn.modules.loss.SmoothL1Loss.html
@@ -4415,7 +4415,7 @@
 <h1>SmoothL1Loss<a class="headerlink" href="#smoothl1loss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.SmoothL1Loss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">SmoothL1Loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L995"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.SmoothL1Loss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">SmoothL1Loss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L995"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.SmoothL1Loss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that uses a squared term if the absolute
 element-wise error falls below beta and an L1 term otherwise.
 It is less sensitive to outliers than <a class="reference internal" href="torch.nn.MSELoss.html#torch.nn.MSELoss" title="torch.nn.MSELoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.MSELoss</span></code></a> and in some cases
@@ -4492,7 +4492,7 @@ <h1>SmoothL1Loss<a class="headerlink" href="#smoothl1loss" title="Permalink to t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.SmoothL1Loss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1075"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.SmoothL1Loss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1075"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.SmoothL1Loss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.SoftMarginLoss.html b/2.9/generated/torch.nn.modules.loss.SoftMarginLoss.html
index be78229651e..8a160371111 100644
--- a/2.9/generated/torch.nn.modules.loss.SoftMarginLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.SoftMarginLoss.html
@@ -4415,7 +4415,7 @@
 <h1>SoftMarginLoss<a class="headerlink" href="#softmarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.SoftMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">SoftMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1142"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.SoftMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">SoftMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1142"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.SoftMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that optimizes a two-class classification
 logistic loss between input tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi></mrow><annotation encoding="application/x-tex">x</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">x</span></span></span></span></span> and target tensor <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>y</mi></mrow><annotation encoding="application/x-tex">y</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span></span></span></span></span>
 (containing 1 or -1).</p>
@@ -4454,7 +4454,7 @@ <h1>SoftMarginLoss<a class="headerlink" href="#softmarginloss" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.SoftMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1180"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.SoftMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1180"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.SoftMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.TripletMarginLoss.html b/2.9/generated/torch.nn.modules.loss.TripletMarginLoss.html
index 37917b3ccf5..9b3c7a960fb 100644
--- a/2.9/generated/torch.nn.modules.loss.TripletMarginLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.TripletMarginLoss.html
@@ -4415,7 +4415,7 @@
 <h1>TripletMarginLoss<a class="headerlink" href="#tripletmarginloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.TripletMarginLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">TripletMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1687"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.TripletMarginLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">TripletMarginLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size_average</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1687"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.TripletMarginLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the triplet loss given an input
 tensors <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>1</mn></mrow><annotation encoding="application/x-tex">x1</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">1</span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>2</mn></mrow><annotation encoding="application/x-tex">x2</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">2</span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>x</mi><mn>3</mn></mrow><annotation encoding="application/x-tex">x3</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord mathnormal">x</span><span class="mord">3</span></span></span></span></span> and a margin with a value greater than <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mn>0</mn></mrow><annotation encoding="application/x-tex">0</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6444em;"></span><span class="mord">0</span></span></span></span></span>.
 This is used for measuring a relative similarity between samples. A triplet
@@ -4483,7 +4483,7 @@ <h1>TripletMarginLoss<a class="headerlink" href="#tripletmarginloss" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.TripletMarginLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1783"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.TripletMarginLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1783"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.TripletMarginLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.loss.TripletMarginWithDistanceLoss.html b/2.9/generated/torch.nn.modules.loss.TripletMarginWithDistanceLoss.html
index b81a4349c31..b48c9414193 100644
--- a/2.9/generated/torch.nn.modules.loss.TripletMarginWithDistanceLoss.html
+++ b/2.9/generated/torch.nn.modules.loss.TripletMarginWithDistanceLoss.html
@@ -4415,7 +4415,7 @@
 <h1>TripletMarginWithDistanceLoss<a class="headerlink" href="#tripletmarginwithdistanceloss" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.TripletMarginWithDistanceLoss">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">TripletMarginWithDistanceLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">distance_function</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1797"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.TripletMarginWithDistanceLoss" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.loss.</span></span><span class="sig-name descname"><span class="pre">TripletMarginWithDistanceLoss</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">distance_function</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">margin</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1797"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.TripletMarginWithDistanceLoss" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a criterion that measures the triplet loss given input
 tensors <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>a</mi></mrow><annotation encoding="application/x-tex">a</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">a</span></span></span></span></span>, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>p</mi></mrow><annotation encoding="application/x-tex">p</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord mathnormal">p</span></span></span></span></span>, and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>n</mi></mrow><annotation encoding="application/x-tex">n</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.4306em;"></span><span class="mord mathnormal">n</span></span></span></span></span> (representing anchor,
 positive, and negative examples, respectively), and a nonnegative,
@@ -4516,7 +4516,7 @@ <h1>TripletMarginWithDistanceLoss<a class="headerlink" href="#tripletmarginwithd
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.loss.TripletMarginWithDistanceLoss.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/loss.py#L1919"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.TripletMarginWithDistanceLoss.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">anchor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">positive</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">negative</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/loss.py#L1919"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.loss.TripletMarginWithDistanceLoss.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.module.register_module_backward_hook.html b/2.9/generated/torch.nn.modules.module.register_module_backward_hook.html
index 7501b595d64..084540f7348 100644
--- a/2.9/generated/torch.nn.modules.module.register_module_backward_hook.html
+++ b/2.9/generated/torch.nn.modules.module.register_module_backward_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.modules.module.register_module_backward_hook<a class="headerlink" href="#torch-nn-modules-module-register-module-backward-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.modules.module.register_module_backward_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L293"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_backward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L293"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_backward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook common to all the modules.</p>
 <p>This function is deprecated in favor of
 <a class="reference internal" href="torch.nn.modules.module.register_module_full_backward_hook.html#torch.nn.modules.module.register_module_full_backward_hook" title="torch.nn.modules.module.register_module_full_backward_hook"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.modules.module.register_module_full_backward_hook()</span></code></a>
diff --git a/2.9/generated/torch.nn.modules.module.register_module_buffer_registration_hook.html b/2.9/generated/torch.nn.modules.module.register_module_buffer_registration_hook.html
index a8981653858..4bb366c42d1 100644
--- a/2.9/generated/torch.nn.modules.module.register_module_buffer_registration_hook.html
+++ b/2.9/generated/torch.nn.modules.module.register_module_buffer_registration_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.modules.module.register_module_buffer_registration_hook<a class="headerlink" href="#torch-nn-modules-module-register-module-buffer-registration-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.modules.module.register_module_buffer_registration_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_buffer_registration_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_buffer_registration_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_buffer_registration_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_buffer_registration_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a buffer registration hook common to all modules.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.modules.module.register_module_forward_hook.html b/2.9/generated/torch.nn.modules.module.register_module_forward_hook.html
index c05a7e4fc1d..6be3e22902d 100644
--- a/2.9/generated/torch.nn.modules.module.register_module_forward_hook.html
+++ b/2.9/generated/torch.nn.modules.module.register_module_forward_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.modules.module.register_module_forward_hook<a class="headerlink" href="#torch-nn-modules-module-register-module-forward-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.modules.module.register_module_forward_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_forward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">always_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L246"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_forward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_forward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">always_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L246"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_forward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a global forward hook for all the modules.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.modules.module.register_module_forward_pre_hook.html b/2.9/generated/torch.nn.modules.module.register_module_forward_pre_hook.html
index 45d96642bc8..a9d605a9a5a 100644
--- a/2.9/generated/torch.nn.modules.module.register_module_forward_pre_hook.html
+++ b/2.9/generated/torch.nn.modules.module.register_module_forward_pre_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.modules.module.register_module_forward_pre_hook<a class="headerlink" href="#torch-nn-modules-module-register-module-forward-pre-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.modules.module.register_module_forward_pre_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_forward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_forward_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_forward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_forward_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a forward pre-hook common to all modules.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.modules.module.register_module_full_backward_hook.html b/2.9/generated/torch.nn.modules.module.register_module_full_backward_hook.html
index f559196cb7e..21e705f5551 100644
--- a/2.9/generated/torch.nn.modules.module.register_module_full_backward_hook.html
+++ b/2.9/generated/torch.nn.modules.module.register_module_full_backward_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.modules.module.register_module_full_backward_hook<a class="headerlink" href="#torch-nn-modules-module-register-module-full-backward-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.modules.module.register_module_full_backward_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_full_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_full_backward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_full_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_full_backward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook common to all the modules.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.modules.module.register_module_full_backward_pre_hook.html b/2.9/generated/torch.nn.modules.module.register_module_full_backward_pre_hook.html
index a507af67f04..9e24eaa28a9 100644
--- a/2.9/generated/torch.nn.modules.module.register_module_full_backward_pre_hook.html
+++ b/2.9/generated/torch.nn.modules.module.register_module_full_backward_pre_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.modules.module.register_module_full_backward_pre_hook<a class="headerlink" href="#torch-nn-modules-module-register-module-full-backward-pre-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.modules.module.register_module_full_backward_pre_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_full_backward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L322"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_full_backward_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_full_backward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L322"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_full_backward_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward pre-hook common to all the modules.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.modules.module.register_module_module_registration_hook.html b/2.9/generated/torch.nn.modules.module.register_module_module_registration_hook.html
index e384467e0b4..7f62e20cb17 100644
--- a/2.9/generated/torch.nn.modules.module.register_module_module_registration_hook.html
+++ b/2.9/generated/torch.nn.modules.module.register_module_module_registration_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.modules.module.register_module_module_registration_hook<a class="headerlink" href="#torch-nn-modules-module-register-module-module-registration-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.modules.module.register_module_module_registration_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_module_registration_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_module_registration_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_module_registration_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_module_registration_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a module registration hook common to all modules.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.modules.module.register_module_parameter_registration_hook.html b/2.9/generated/torch.nn.modules.module.register_module_parameter_registration_hook.html
index 96004ba03ea..93e3037c0a5 100644
--- a/2.9/generated/torch.nn.modules.module.register_module_parameter_registration_hook.html
+++ b/2.9/generated/torch.nn.modules.module.register_module_parameter_registration_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.modules.module.register_module_parameter_registration_hook<a class="headerlink" href="#torch-nn-modules-module-register-module-parameter-registration-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.modules.module.register_module_parameter_registration_hook">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_parameter_registration_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_parameter_registration_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.modules.module.</span></span><span class="sig-name descname"><span class="pre">register_module_parameter_registration_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.module.register_module_parameter_registration_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a parameter registration hook common to all modules.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.modules.normalization.GroupNorm.html b/2.9/generated/torch.nn.modules.normalization.GroupNorm.html
index 745a0288e2a..42d4ddbfb27 100644
--- a/2.9/generated/torch.nn.modules.normalization.GroupNorm.html
+++ b/2.9/generated/torch.nn.modules.normalization.GroupNorm.html
@@ -4415,7 +4415,7 @@
 <h1>GroupNorm<a class="headerlink" href="#groupnorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.GroupNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.normalization.</span></span><span class="sig-name descname"><span class="pre">GroupNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_groups</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.GroupNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.normalization.</span></span><span class="sig-name descname"><span class="pre">GroupNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_groups</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_channels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.GroupNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Group Normalization over a mini-batch of inputs.</p>
 <p>This layer implements the operation as described in
 the paper <a class="reference external" href="https://arxiv.org/abs/1803.08494">Group Normalization</a></p>
diff --git a/2.9/generated/torch.nn.modules.normalization.LayerNorm.html b/2.9/generated/torch.nn.modules.normalization.LayerNorm.html
index 9778454527f..34bea248869 100644
--- a/2.9/generated/torch.nn.modules.normalization.LayerNorm.html
+++ b/2.9/generated/torch.nn.modules.normalization.LayerNorm.html
@@ -4415,7 +4415,7 @@
 <h1>LayerNorm<a class="headerlink" href="#layernorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.LayerNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.normalization.</span></span><span class="sig-name descname"><span class="pre">LayerNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L106"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.LayerNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.normalization.</span></span><span class="sig-name descname"><span class="pre">LayerNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L106"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.LayerNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Layer Normalization over a mini-batch of inputs.</p>
 <p>This layer implements the operation as described in
 the paper <a class="reference external" href="https://arxiv.org/abs/1607.06450">Layer Normalization</a></p>
diff --git a/2.9/generated/torch.nn.modules.normalization.LocalResponseNorm.html b/2.9/generated/torch.nn.modules.normalization.LocalResponseNorm.html
index 92c5a3e30f5..501c6e3dd0a 100644
--- a/2.9/generated/torch.nn.modules.normalization.LocalResponseNorm.html
+++ b/2.9/generated/torch.nn.modules.normalization.LocalResponseNorm.html
@@ -4415,7 +4415,7 @@
 <h1>LocalResponseNorm<a class="headerlink" href="#localresponsenorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.LocalResponseNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.normalization.</span></span><span class="sig-name descname"><span class="pre">LocalResponseNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.LocalResponseNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.normalization.</span></span><span class="sig-name descname"><span class="pre">LocalResponseNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">k</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L17"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.LocalResponseNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies local response normalization over an input signal.</p>
 <p>The input signal is composed of several input planes, where channels occupy the second dimension.
 Applies normalization across channels.</p>
@@ -4465,13 +4465,13 @@ <h1>LocalResponseNorm<a class="headerlink" href="#localresponsenorm" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.LocalResponseNorm.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.LocalResponseNorm.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L68"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.LocalResponseNorm.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.LocalResponseNorm.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.LocalResponseNorm.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.LocalResponseNorm.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.normalization.RMSNorm.html b/2.9/generated/torch.nn.modules.normalization.RMSNorm.html
index 79756d117fb..7c21ae4fe0d 100644
--- a/2.9/generated/torch.nn.modules.normalization.RMSNorm.html
+++ b/2.9/generated/torch.nn.modules.normalization.RMSNorm.html
@@ -4415,7 +4415,7 @@
 <h1>RMSNorm<a class="headerlink" href="#rmsnorm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.RMSNorm">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.normalization.</span></span><span class="sig-name descname"><span class="pre">RMSNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L333"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.RMSNorm" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.normalization.</span></span><span class="sig-name descname"><span class="pre">RMSNorm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalized_shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise_affine</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L333"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.RMSNorm" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies Root Mean Square Layer Normalization over a mini-batch of inputs.</p>
 <p>This layer implements the operation as described in
 the paper <a class="reference external" href="https://arxiv.org/pdf/1910.07467.pdf">Root Mean Square Layer Normalization</a></p>
@@ -4464,7 +4464,7 @@ <h1>RMSNorm<a class="headerlink" href="#rmsnorm" title="Permalink to this headin
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.RMSNorm.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.RMSNorm.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.RMSNorm.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4475,7 +4475,7 @@ <h1>RMSNorm<a class="headerlink" href="#rmsnorm" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.RMSNorm.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.RMSNorm.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.RMSNorm.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4486,7 +4486,7 @@ <h1>RMSNorm<a class="headerlink" href="#rmsnorm" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.normalization.RMSNorm.reset_parameters">
-<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/normalization.py#L403"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.RMSNorm.reset_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/normalization.py#L403"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.normalization.RMSNorm.reset_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Resets parameters based on their initialization used in __init__.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.padding.CircularPad1d.html b/2.9/generated/torch.nn.modules.padding.CircularPad1d.html
index 9fc3c86a916..514b5f0ea9b 100644
--- a/2.9/generated/torch.nn.modules.padding.CircularPad1d.html
+++ b/2.9/generated/torch.nn.modules.padding.CircularPad1d.html
@@ -4415,7 +4415,7 @@
 <h1>CircularPad1d<a class="headerlink" href="#circularpad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.CircularPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">CircularPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.CircularPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">CircularPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.CircularPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using circular padding of the input boundary.</p>
 <p>Tensor values at the beginning of the dimension are used to pad the end,
 and values at the end are used to pad the beginning. If negative padding is
diff --git a/2.9/generated/torch.nn.modules.padding.CircularPad2d.html b/2.9/generated/torch.nn.modules.padding.CircularPad2d.html
index 2aa4f5b15c3..408a33596f8 100644
--- a/2.9/generated/torch.nn.modules.padding.CircularPad2d.html
+++ b/2.9/generated/torch.nn.modules.padding.CircularPad2d.html
@@ -4415,7 +4415,7 @@
 <h1>CircularPad2d<a class="headerlink" href="#circularpad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.CircularPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">CircularPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.CircularPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">CircularPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.CircularPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using circular padding of the input boundary.</p>
 <p>Tensor values at the beginning of the dimension are used to pad the end,
 and values at the end are used to pad the beginning. If negative padding is
diff --git a/2.9/generated/torch.nn.modules.padding.CircularPad3d.html b/2.9/generated/torch.nn.modules.padding.CircularPad3d.html
index 2e4cda0df0f..f300991f830 100644
--- a/2.9/generated/torch.nn.modules.padding.CircularPad3d.html
+++ b/2.9/generated/torch.nn.modules.padding.CircularPad3d.html
@@ -4415,7 +4415,7 @@
 <h1>CircularPad3d<a class="headerlink" href="#circularpad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.CircularPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">CircularPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.CircularPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">CircularPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L158"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.CircularPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using circular padding of the input boundary.</p>
 <p>Tensor values at the beginning of the dimension are used to pad the end,
 and values at the end are used to pad the beginning. If negative padding is
diff --git a/2.9/generated/torch.nn.modules.padding.ConstantPad1d.html b/2.9/generated/torch.nn.modules.padding.ConstantPad1d.html
index 8a494a1ccb3..da3726caaf0 100644
--- a/2.9/generated/torch.nn.modules.padding.ConstantPad1d.html
+++ b/2.9/generated/torch.nn.modules.padding.ConstantPad1d.html
@@ -4415,7 +4415,7 @@
 <h1>ConstantPad1d<a class="headerlink" href="#constantpad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ConstantPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ConstantPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ConstantPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ConstantPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ConstantPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with a constant value.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ConstantPad2d.html b/2.9/generated/torch.nn.modules.padding.ConstantPad2d.html
index 439ef2f6fc9..03b90e19728 100644
--- a/2.9/generated/torch.nn.modules.padding.ConstantPad2d.html
+++ b/2.9/generated/torch.nn.modules.padding.ConstantPad2d.html
@@ -4415,7 +4415,7 @@
 <h1>ConstantPad2d<a class="headerlink" href="#constantpad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ConstantPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ConstantPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ConstantPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ConstantPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ConstantPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with a constant value.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ConstantPad3d.html b/2.9/generated/torch.nn.modules.padding.ConstantPad3d.html
index cd4203345d4..28bc446b783 100644
--- a/2.9/generated/torch.nn.modules.padding.ConstantPad3d.html
+++ b/2.9/generated/torch.nn.modules.padding.ConstantPad3d.html
@@ -4415,7 +4415,7 @@
 <h1>ConstantPad3d<a class="headerlink" href="#constantpad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ConstantPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ConstantPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ConstantPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ConstantPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ConstantPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with a constant value.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ReflectionPad1d.html b/2.9/generated/torch.nn.modules.padding.ReflectionPad1d.html
index f842b92ab0b..7f764b18578 100644
--- a/2.9/generated/torch.nn.modules.padding.ReflectionPad1d.html
+++ b/2.9/generated/torch.nn.modules.padding.ReflectionPad1d.html
@@ -4415,7 +4415,7 @@
 <h1>ReflectionPad1d<a class="headerlink" href="#reflectionpad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ReflectionPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReflectionPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReflectionPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using the reflection of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ReflectionPad2d.html b/2.9/generated/torch.nn.modules.padding.ReflectionPad2d.html
index 30d94e811b7..ddc90d45add 100644
--- a/2.9/generated/torch.nn.modules.padding.ReflectionPad2d.html
+++ b/2.9/generated/torch.nn.modules.padding.ReflectionPad2d.html
@@ -4415,7 +4415,7 @@
 <h1>ReflectionPad2d<a class="headerlink" href="#reflectionpad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ReflectionPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReflectionPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReflectionPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using the reflection of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ReflectionPad3d.html b/2.9/generated/torch.nn.modules.padding.ReflectionPad3d.html
index 9b9cb9f617d..f14fb0e255a 100644
--- a/2.9/generated/torch.nn.modules.padding.ReflectionPad3d.html
+++ b/2.9/generated/torch.nn.modules.padding.ReflectionPad3d.html
@@ -4415,7 +4415,7 @@
 <h1>ReflectionPad3d<a class="headerlink" href="#reflectionpad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ReflectionPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L472"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReflectionPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReflectionPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L472"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReflectionPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using the reflection of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ReplicationPad1d.html b/2.9/generated/torch.nn.modules.padding.ReplicationPad1d.html
index 4c7035cc4a1..a4052ae6a8d 100644
--- a/2.9/generated/torch.nn.modules.padding.ReplicationPad1d.html
+++ b/2.9/generated/torch.nn.modules.padding.ReplicationPad1d.html
@@ -4415,7 +4415,7 @@
 <h1>ReplicationPad1d<a class="headerlink" href="#replicationpad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ReplicationPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReplicationPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReplicationPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using replication of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ReplicationPad2d.html b/2.9/generated/torch.nn.modules.padding.ReplicationPad2d.html
index c1a0def2993..67edf416119 100644
--- a/2.9/generated/torch.nn.modules.padding.ReplicationPad2d.html
+++ b/2.9/generated/torch.nn.modules.padding.ReplicationPad2d.html
@@ -4415,7 +4415,7 @@
 <h1>ReplicationPad2d<a class="headerlink" href="#replicationpad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ReplicationPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReplicationPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReplicationPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using replication of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ReplicationPad3d.html b/2.9/generated/torch.nn.modules.padding.ReplicationPad3d.html
index d6c608462b0..ab1a0c451b1 100644
--- a/2.9/generated/torch.nn.modules.padding.ReplicationPad3d.html
+++ b/2.9/generated/torch.nn.modules.padding.ReplicationPad3d.html
@@ -4415,7 +4415,7 @@
 <h1>ReplicationPad3d<a class="headerlink" href="#replicationpad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ReplicationPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReplicationPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ReplicationPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ReplicationPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor using replication of the input boundary.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.padding.ZeroPad1d.html b/2.9/generated/torch.nn.modules.padding.ZeroPad1d.html
index b9320272d62..98986e3a56c 100644
--- a/2.9/generated/torch.nn.modules.padding.ZeroPad1d.html
+++ b/2.9/generated/torch.nn.modules.padding.ZeroPad1d.html
@@ -4415,7 +4415,7 @@
 <h1>ZeroPad1d<a class="headerlink" href="#zeropad1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ZeroPad1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ZeroPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ZeroPad1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L675"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with zero.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4462,7 +4462,7 @@ <h1>ZeroPad1d<a class="headerlink" href="#zeropad1d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ZeroPad1d.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad1d.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad1d.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.padding.ZeroPad2d.html b/2.9/generated/torch.nn.modules.padding.ZeroPad2d.html
index 79fd473ed49..eac635da19f 100644
--- a/2.9/generated/torch.nn.modules.padding.ZeroPad2d.html
+++ b/2.9/generated/torch.nn.modules.padding.ZeroPad2d.html
@@ -4415,7 +4415,7 @@
 <h1>ZeroPad2d<a class="headerlink" href="#zeropad2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ZeroPad2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ZeroPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L731"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ZeroPad2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L731"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with zero.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4462,7 +4462,7 @@ <h1>ZeroPad2d<a class="headerlink" href="#zeropad2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ZeroPad2d.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad2d.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad2d.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.padding.ZeroPad3d.html b/2.9/generated/torch.nn.modules.padding.ZeroPad3d.html
index 8dfccccbd8b..6716c9ab7f4 100644
--- a/2.9/generated/torch.nn.modules.padding.ZeroPad3d.html
+++ b/2.9/generated/torch.nn.modules.padding.ZeroPad3d.html
@@ -4415,7 +4415,7 @@
 <h1>ZeroPad3d<a class="headerlink" href="#zeropad3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ZeroPad3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ZeroPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L788"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.padding.</span></span><span class="sig-name descname"><span class="pre">ZeroPad3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padding</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L788"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Pads the input tensor boundaries with zero.</p>
 <p>For <cite>N</cite>-dimensional padding, use <a class="reference internal" href="torch.nn.functional.pad.html#torch.nn.functional.pad" title="torch.nn.functional.pad"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.nn.functional.pad()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4450,7 +4450,7 @@ <h1>ZeroPad3d<a class="headerlink" href="#zeropad3d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.padding.ZeroPad3d.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/padding.py#L826"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad3d.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/padding.py#L826"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.padding.ZeroPad3d.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pixelshuffle.PixelShuffle.html b/2.9/generated/torch.nn.modules.pixelshuffle.PixelShuffle.html
index e91a564ac52..d18d880a9c2 100644
--- a/2.9/generated/torch.nn.modules.pixelshuffle.PixelShuffle.html
+++ b/2.9/generated/torch.nn.modules.pixelshuffle.PixelShuffle.html
@@ -4415,7 +4415,7 @@
 <h1>PixelShuffle<a class="headerlink" href="#pixelshuffle" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pixelshuffle.PixelShuffle">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pixelshuffle.</span></span><span class="sig-name descname"><span class="pre">PixelShuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">upscale_factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelShuffle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pixelshuffle.</span></span><span class="sig-name descname"><span class="pre">PixelShuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">upscale_factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelShuffle" title="Permalink to this definition">#</a></dt>
 <dd><p>Rearrange elements in a tensor according to an upscaling factor.</p>
 <p>Rearranges elements in a tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mo>∗</mo><mo separator="true">,</mo><mi>C</mi><mo>×</mo><msup><mi>r</mi><mn>2</mn></msup><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(*, C \times r^2, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord">∗</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1.0641em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8141em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>
 to a tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mo>∗</mo><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>H</mi><mo>×</mo><mi>r</mi><mo separator="true">,</mo><mi>W</mi><mo>×</mo><mi>r</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(*, C, H \times r, W \times r)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord">∗</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8778em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="mclose">)</span></span></span></span></span>, where r is an upscale factor.</p>
@@ -4455,7 +4455,7 @@ <h1>PixelShuffle<a class="headerlink" href="#pixelshuffle" title="Permalink to t
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pixelshuffle.PixelShuffle.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelShuffle.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelShuffle.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4466,7 +4466,7 @@ <h1>PixelShuffle<a class="headerlink" href="#pixelshuffle" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pixelshuffle.PixelShuffle.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelShuffle.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelShuffle.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pixelshuffle.PixelUnshuffle.html b/2.9/generated/torch.nn.modules.pixelshuffle.PixelUnshuffle.html
index 4baf3ffe858..18706139c36 100644
--- a/2.9/generated/torch.nn.modules.pixelshuffle.PixelUnshuffle.html
+++ b/2.9/generated/torch.nn.modules.pixelshuffle.PixelUnshuffle.html
@@ -4415,7 +4415,7 @@
 <h1>PixelUnshuffle<a class="headerlink" href="#pixelunshuffle" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pixelshuffle.PixelUnshuffle">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pixelshuffle.</span></span><span class="sig-name descname"><span class="pre">PixelUnshuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">downscale_factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelUnshuffle" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pixelshuffle.</span></span><span class="sig-name descname"><span class="pre">PixelUnshuffle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">downscale_factor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelUnshuffle" title="Permalink to this definition">#</a></dt>
 <dd><p>Reverse the PixelShuffle operation.</p>
 <p>Reverses the <a class="reference internal" href="torch.nn.PixelShuffle.html#torch.nn.PixelShuffle" title="torch.nn.PixelShuffle"><code class="xref py py-class docutils literal notranslate"><span class="pre">PixelShuffle</span></code></a> operation by rearranging elements
 in a tensor of shape <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mo>∗</mo><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>H</mi><mo>×</mo><mi>r</mi><mo separator="true">,</mo><mi>W</mi><mo>×</mo><mi>r</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(*, C, H \times r, W \times r)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord">∗</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8778em;vertical-align:-0.1944em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">r</span><span class="mclose">)</span></span></span></span></span> to a tensor of shape
@@ -4454,7 +4454,7 @@ <h1>PixelUnshuffle<a class="headerlink" href="#pixelunshuffle" title="Permalink
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pixelshuffle.PixelUnshuffle.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L123"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelUnshuffle.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L123"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelUnshuffle.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4465,7 +4465,7 @@ <h1>PixelUnshuffle<a class="headerlink" href="#pixelunshuffle" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pixelshuffle.PixelUnshuffle.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pixelshuffle.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelUnshuffle.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pixelshuffle.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pixelshuffle.PixelUnshuffle.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool1d.html b/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool1d.html
index 46e32481298..a4020b31add 100644
--- a/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool1d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool1d.html
@@ -4415,7 +4415,7 @@
 <h1>AdaptiveAvgPool1d<a class="headerlink" href="#adaptiveavgpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveAvgPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1432"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1432"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D adaptive average pooling over an input signal composed of several input planes.</p>
 <p>The output size is <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>L</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub></mrow><annotation encoding="application/x-tex">L_{out}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4441,7 +4441,7 @@ <h1>AdaptiveAvgPool1d<a class="headerlink" href="#adaptiveavgpool1d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveAvgPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1456"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1456"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool2d.html b/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool2d.html
index c9b1d573f53..4c7576043fb 100644
--- a/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool2d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool2d.html
@@ -4415,7 +4415,7 @@
 <h1>AdaptiveAvgPool2d<a class="headerlink" href="#adaptiveavgpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveAvgPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1463"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1463"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D adaptive average pooling over an input signal composed of several input planes.</p>
 <p>The output is of size H x W, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4452,7 +4452,7 @@ <h1>AdaptiveAvgPool2d<a class="headerlink" href="#adaptiveavgpool2d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveAvgPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1498"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool3d.html b/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool3d.html
index d7b2b451174..0b5897d27ee 100644
--- a/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool3d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AdaptiveAvgPool3d.html
@@ -4415,7 +4415,7 @@
 <h1>AdaptiveAvgPool3d<a class="headerlink" href="#adaptiveavgpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveAvgPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1503"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveAvgPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1503"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D adaptive average pooling over an input signal composed of several input planes.</p>
 <p>The output is of size D x H x W, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4452,7 +4452,7 @@ <h1>AdaptiveAvgPool3d<a class="headerlink" href="#adaptiveavgpool3d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveAvgPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1538"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveAvgPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool1d.html b/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool1d.html
index 694b9e07200..1f979647912 100644
--- a/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool1d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool1d.html
@@ -4415,7 +4415,7 @@
 <h1>AdaptiveMaxPool1d<a class="headerlink" href="#adaptivemaxpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveMaxPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1303"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D adaptive max pooling over an input signal composed of several input planes.</p>
 <p>The output size is <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>L</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub></mrow><annotation encoding="application/x-tex">L_{out}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4445,7 +4445,7 @@ <h1>AdaptiveMaxPool1d<a class="headerlink" href="#adaptivemaxpool1d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveMaxPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1329"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1329"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool2d.html b/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool2d.html
index 792f0acbf9d..94c650cabea 100644
--- a/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool2d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool2d.html
@@ -4415,7 +4415,7 @@
 <h1>AdaptiveMaxPool2d<a class="headerlink" href="#adaptivemaxpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveMaxPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D adaptive max pooling over an input signal composed of several input planes.</p>
 <p>The output is of size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo>×</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub></mrow><annotation encoding="application/x-tex">H_{out} \times W_{out}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4457,7 +4457,7 @@ <h1>AdaptiveMaxPool2d<a class="headerlink" href="#adaptivemaxpool2d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveMaxPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1372"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1372"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool3d.html b/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool3d.html
index c510d7b0755..67743ad70ac 100644
--- a/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool3d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AdaptiveMaxPool3d.html
@@ -4415,7 +4415,7 @@
 <h1>AdaptiveMaxPool3d<a class="headerlink" href="#adaptivemaxpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveMaxPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AdaptiveMaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D adaptive max pooling over an input signal composed of several input planes.</p>
 <p>The output is of size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>D</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo>×</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo>×</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub></mrow><annotation encoding="application/x-tex">D_{out} \times H_{out} \times W_{out}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, for any input size.
 The number of output features is equal to the number of input planes.</p>
@@ -4457,7 +4457,7 @@ <h1>AdaptiveMaxPool3d<a class="headerlink" href="#adaptivemaxpool3d" title="Perm
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AdaptiveMaxPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AdaptiveMaxPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.pooling.AvgPool1d.html b/2.9/generated/torch.nn.modules.pooling.AvgPool1d.html
index b42604a1a88..11d4010bd25 100644
--- a/2.9/generated/torch.nn.modules.pooling.AvgPool1d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AvgPool1d.html
@@ -4415,7 +4415,7 @@
 <h1>AvgPool1d<a class="headerlink" href="#avgpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AvgPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AvgPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AvgPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D average pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>L</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, L)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">L</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>L</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, L_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi></mrow><annotation encoding="application/x-tex">k</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span></span></span></span></span>
@@ -4470,7 +4470,7 @@ <h1>AvgPool1d<a class="headerlink" href="#avgpool1d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AvgPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L670"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L670"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.AvgPool2d.html b/2.9/generated/torch.nn.modules.pooling.AvgPool2d.html
index 5b31a19d7de..a72204cbef7 100644
--- a/2.9/generated/torch.nn.modules.pooling.AvgPool2d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AvgPool2d.html
@@ -4415,7 +4415,7 @@
 <h1>AvgPool2d<a class="headerlink" href="#avgpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AvgPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AvgPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L682"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AvgPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L682"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D average pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, H_{out}, W_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>k</mi><mi>H</mi><mo separator="true">,</mo><mi>k</mi><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(kH, kW)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span><span class="mclose">)</span></span></span></span></span>
@@ -4484,7 +4484,7 @@ <h1>AvgPool2d<a class="headerlink" href="#avgpool2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AvgPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L779"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L779"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.AvgPool3d.html b/2.9/generated/torch.nn.modules.pooling.AvgPool3d.html
index 9ef0bf6f29d..494c55929d5 100644
--- a/2.9/generated/torch.nn.modules.pooling.AvgPool3d.html
+++ b/2.9/generated/torch.nn.modules.pooling.AvgPool3d.html
@@ -4415,7 +4415,7 @@
 <h1>AvgPool3d<a class="headerlink" href="#avgpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AvgPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AvgPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L792"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">AvgPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">count_include_pad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">divisor_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L792"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D average pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>D</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, D, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>D</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, D_{out}, H_{out}, W_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>k</mi><mi>D</mi><mo separator="true">,</mo><mi>k</mi><mi>H</mi><mo separator="true">,</mo><mi>k</mi><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(kD, kH, kW)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span><span class="mclose">)</span></span></span></span></span>
@@ -4495,7 +4495,7 @@ <h1>AvgPool3d<a class="headerlink" href="#avgpool3d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.AvgPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L896"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L896"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.AvgPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.FractionalMaxPool2d.html b/2.9/generated/torch.nn.modules.pooling.FractionalMaxPool2d.html
index 9c3e1ac56ca..03263badea2 100644
--- a/2.9/generated/torch.nn.modules.pooling.FractionalMaxPool2d.html
+++ b/2.9/generated/torch.nn.modules.pooling.FractionalMaxPool2d.html
@@ -4415,7 +4415,7 @@
 <h1>FractionalMaxPool2d<a class="headerlink" href="#fractionalmaxpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.FractionalMaxPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">FractionalMaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L915"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.FractionalMaxPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">FractionalMaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L915"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.FractionalMaxPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D fractional max pooling over an input signal composed of several input planes.</p>
 <p>Fractional MaxPooling is described in detail in the paper <a class="reference external" href="https://arxiv.org/abs/1412.6071">Fractional MaxPooling</a> by Ben Graham</p>
 <p>The max-pooling operation is applied in <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi><mi>H</mi><mo>×</mo><mi>k</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">kH \times kW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span></span></span></span></span> regions by a stochastic
diff --git a/2.9/generated/torch.nn.modules.pooling.FractionalMaxPool3d.html b/2.9/generated/torch.nn.modules.pooling.FractionalMaxPool3d.html
index f74e1e7d32b..39159076fbe 100644
--- a/2.9/generated/torch.nn.modules.pooling.FractionalMaxPool3d.html
+++ b/2.9/generated/torch.nn.modules.pooling.FractionalMaxPool3d.html
@@ -4415,7 +4415,7 @@
 <h1>FractionalMaxPool3d<a class="headerlink" href="#fractionalmaxpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.FractionalMaxPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">FractionalMaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1004"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.FractionalMaxPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">FractionalMaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_ratio</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_random_samples</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1004"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.FractionalMaxPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D fractional max pooling over an input signal composed of several input planes.</p>
 <p>Fractional MaxPooling is described in detail in the paper <a class="reference external" href="https://arxiv.org/abs/1412.6071">Fractional MaxPooling</a> by Ben Graham</p>
 <p>The max-pooling operation is applied in <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>k</mi><mi>T</mi><mo>×</mo><mi>k</mi><mi>H</mi><mo>×</mo><mi>k</mi><mi>W</mi></mrow><annotation encoding="application/x-tex">kT \times kH \times kW</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.13889em;">T</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.7778em;vertical-align:-0.0833em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span></span></span></span></span> regions by a stochastic
diff --git a/2.9/generated/torch.nn.modules.pooling.LPPool1d.html b/2.9/generated/torch.nn.modules.pooling.LPPool1d.html
index 9bb2f23608b..b772ad440e0 100644
--- a/2.9/generated/torch.nn.modules.pooling.LPPool1d.html
+++ b/2.9/generated/torch.nn.modules.pooling.LPPool1d.html
@@ -4415,7 +4415,7 @@
 <h1>LPPool1d<a class="headerlink" href="#lppool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.LPPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">LPPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">LPPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D power-average pooling over an input signal composed of several input planes.</p>
 <p>On each window, the function computed is:</p>
 <div class="math">
@@ -4466,7 +4466,7 @@ <h1>LPPool1d<a class="headerlink" href="#lppool1d" title="Permalink to this head
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.LPPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.LPPool2d.html b/2.9/generated/torch.nn.modules.pooling.LPPool2d.html
index 35bf88ef864..3d1073a6fe5 100644
--- a/2.9/generated/torch.nn.modules.pooling.LPPool2d.html
+++ b/2.9/generated/torch.nn.modules.pooling.LPPool2d.html
@@ -4415,7 +4415,7 @@
 <h1>LPPool2d<a class="headerlink" href="#lppool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.LPPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">LPPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">LPPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D power-average pooling over an input signal composed of several input planes.</p>
 <p>On each window, the function computed is:</p>
 <div class="math">
@@ -4479,7 +4479,7 @@ <h1>LPPool2d<a class="headerlink" href="#lppool2d" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.LPPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.LPPool3d.html b/2.9/generated/torch.nn.modules.pooling.LPPool3d.html
index f365da0d0b3..f9045cf17b0 100644
--- a/2.9/generated/torch.nn.modules.pooling.LPPool3d.html
+++ b/2.9/generated/torch.nn.modules.pooling.LPPool3d.html
@@ -4415,7 +4415,7 @@
 <h1>LPPool3d<a class="headerlink" href="#lppool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.LPPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">LPPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">LPPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">norm_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D power-average pooling over an input signal composed of several input planes.</p>
 <p>On each window, the function computed is:</p>
 <div class="math">
@@ -4483,7 +4483,7 @@ <h1>LPPool3d<a class="headerlink" href="#lppool3d" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.LPPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L1277"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L1277"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.LPPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.MaxPool1d.html b/2.9/generated/torch.nn.modules.pooling.MaxPool1d.html
index 7b5291bb0c9..d1fa4c5a413 100644
--- a/2.9/generated/torch.nn.modules.pooling.MaxPool1d.html
+++ b/2.9/generated/torch.nn.modules.pooling.MaxPool1d.html
@@ -4415,7 +4415,7 @@
 <h1>MaxPool1d<a class="headerlink" href="#maxpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxPool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L81"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxPool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L81"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 1D max pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>L</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, L)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">L</span><span class="mclose">)</span></span></span></span></span>
 and output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>L</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, L_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> can be precisely described as:</p>
@@ -4474,7 +4474,7 @@ <h1>MaxPool1d<a class="headerlink" href="#maxpool1d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxPool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.pooling.MaxPool2d.html b/2.9/generated/torch.nn.modules.pooling.MaxPool2d.html
index a30feb35c19..1ac07dae17e 100644
--- a/2.9/generated/torch.nn.modules.pooling.MaxPool2d.html
+++ b/2.9/generated/torch.nn.modules.pooling.MaxPool2d.html
@@ -4415,7 +4415,7 @@
 <h1>MaxPool2d<a class="headerlink" href="#maxpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxPool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxPool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D max pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, H_{out}, W_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>k</mi><mi>H</mi><mo separator="true">,</mo><mi>k</mi><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(kH, kW)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span><span class="mclose">)</span></span></span></span></span>
@@ -4483,7 +4483,7 @@ <h1>MaxPool2d<a class="headerlink" href="#maxpool2d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxPool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.pooling.MaxPool3d.html b/2.9/generated/torch.nn.modules.pooling.MaxPool3d.html
index 0317e640fbe..dc639514938 100644
--- a/2.9/generated/torch.nn.modules.pooling.MaxPool3d.html
+++ b/2.9/generated/torch.nn.modules.pooling.MaxPool3d.html
@@ -4415,7 +4415,7 @@
 <h1>MaxPool3d<a class="headerlink" href="#maxpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxPool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxPool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dilation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ceil_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L237"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 3D max pooling over an input signal composed of several input planes.</p>
 <p>In the simplest case, the output value of the layer with input size <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><mi>D</mi><mo separator="true">,</mo><mi>H</mi><mo separator="true">,</mo><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, D, H, W)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="mclose">)</span></span></span></span></span>,
 output <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>N</mi><mo separator="true">,</mo><mi>C</mi><mo separator="true">,</mo><msub><mi>D</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>H</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo separator="true">,</mo><msub><mi>W</mi><mrow><mi>o</mi><mi>u</mi><mi>t</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(N, C, D_{out}, H_{out}, W_{out})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.07153em;">C</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.0813em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2806em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">o</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight">t</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">kernel_size</span></code> <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>k</mi><mi>D</mi><mo separator="true">,</mo><mi>k</mi><mi>H</mi><mo separator="true">,</mo><mi>k</mi><mi>W</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(kD, kH, kW)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.03148em;">k</span><span class="mord mathnormal" style="margin-right:0.08125em;">H</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal" style="margin-right:0.13889em;">kW</span><span class="mclose">)</span></span></span></span></span>
@@ -4487,7 +4487,7 @@ <h1>MaxPool3d<a class="headerlink" href="#maxpool3d" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxPool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L308"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L308"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxPool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.nn.modules.pooling.MaxUnpool1d.html b/2.9/generated/torch.nn.modules.pooling.MaxUnpool1d.html
index 80f67788b2b..35171b9cd9b 100644
--- a/2.9/generated/torch.nn.modules.pooling.MaxUnpool1d.html
+++ b/2.9/generated/torch.nn.modules.pooling.MaxUnpool1d.html
@@ -4415,7 +4415,7 @@
 <h1>MaxUnpool1d<a class="headerlink" href="#maxunpool1d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxUnpool1d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool1d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool1d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool1d" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a partial inverse of <a class="reference internal" href="torch.nn.modules.pooling.MaxPool1d.html#torch.nn.modules.pooling.MaxPool1d" title="torch.nn.modules.pooling.MaxPool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool1d</span></code></a>.</p>
 <p><a class="reference internal" href="torch.nn.modules.pooling.MaxPool1d.html#torch.nn.modules.pooling.MaxPool1d" title="torch.nn.modules.pooling.MaxPool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool1d</span></code></a> is not fully invertible, since the non-maximal values are lost.</p>
 <p><a class="reference internal" href="#torch.nn.modules.pooling.MaxUnpool1d" title="torch.nn.modules.pooling.MaxUnpool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool1d</span></code></a> takes in as input the output of <a class="reference internal" href="torch.nn.modules.pooling.MaxPool1d.html#torch.nn.modules.pooling.MaxPool1d" title="torch.nn.modules.pooling.MaxPool1d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool1d</span></code></a>
@@ -4482,7 +4482,7 @@ <h1>MaxUnpool1d<a class="headerlink" href="#maxunpool1d" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxUnpool1d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L400"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool1d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L400"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool1d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.MaxUnpool2d.html b/2.9/generated/torch.nn.modules.pooling.MaxUnpool2d.html
index d772a9e2bab..540012369d1 100644
--- a/2.9/generated/torch.nn.modules.pooling.MaxUnpool2d.html
+++ b/2.9/generated/torch.nn.modules.pooling.MaxUnpool2d.html
@@ -4415,7 +4415,7 @@
 <h1>MaxUnpool2d<a class="headerlink" href="#maxunpool2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxUnpool2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a partial inverse of <a class="reference internal" href="torch.nn.modules.pooling.MaxPool2d.html#torch.nn.modules.pooling.MaxPool2d" title="torch.nn.modules.pooling.MaxPool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool2d</span></code></a>.</p>
 <p><a class="reference internal" href="torch.nn.modules.pooling.MaxPool2d.html#torch.nn.modules.pooling.MaxPool2d" title="torch.nn.modules.pooling.MaxPool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool2d</span></code></a> is not fully invertible, since the non-maximal values are lost.</p>
 <p><a class="reference internal" href="#torch.nn.modules.pooling.MaxUnpool2d" title="torch.nn.modules.pooling.MaxUnpool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool2d</span></code></a> takes in as input the output of <a class="reference internal" href="torch.nn.modules.pooling.MaxPool2d.html#torch.nn.modules.pooling.MaxPool2d" title="torch.nn.modules.pooling.MaxPool2d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool2d</span></code></a>
@@ -4494,7 +4494,7 @@ <h1>MaxUnpool2d<a class="headerlink" href="#maxunpool2d" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxUnpool2d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L496"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool2d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L496"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool2d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.pooling.MaxUnpool3d.html b/2.9/generated/torch.nn.modules.pooling.MaxUnpool3d.html
index e4980b08547..d203a26526b 100644
--- a/2.9/generated/torch.nn.modules.pooling.MaxUnpool3d.html
+++ b/2.9/generated/torch.nn.modules.pooling.MaxUnpool3d.html
@@ -4415,7 +4415,7 @@
 <h1>MaxUnpool3d<a class="headerlink" href="#maxunpool3d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxUnpool3d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L505"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool3d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.pooling.</span></span><span class="sig-name descname"><span class="pre">MaxUnpool3d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kernel_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L505"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool3d" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a partial inverse of <a class="reference internal" href="torch.nn.modules.pooling.MaxPool3d.html#torch.nn.modules.pooling.MaxPool3d" title="torch.nn.modules.pooling.MaxPool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool3d</span></code></a>.</p>
 <p><a class="reference internal" href="torch.nn.modules.pooling.MaxPool3d.html#torch.nn.modules.pooling.MaxPool3d" title="torch.nn.modules.pooling.MaxPool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool3d</span></code></a> is not fully invertible, since the non-maximal values are lost.
 <a class="reference internal" href="#torch.nn.modules.pooling.MaxUnpool3d" title="torch.nn.modules.pooling.MaxUnpool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxUnpool3d</span></code></a> takes in as input the output of <a class="reference internal" href="torch.nn.modules.pooling.MaxPool3d.html#torch.nn.modules.pooling.MaxPool3d" title="torch.nn.modules.pooling.MaxPool3d"><code class="xref py py-class docutils literal notranslate"><span class="pre">MaxPool3d</span></code></a>
@@ -4480,7 +4480,7 @@ <h1>MaxUnpool3d<a class="headerlink" href="#maxunpool3d" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.pooling.MaxUnpool3d.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/pooling.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool3d.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/pooling.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.pooling.MaxUnpool3d.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.rnn.GRU.html b/2.9/generated/torch.nn.modules.rnn.GRU.html
index 19ecc8ca714..c91d83e8f48 100644
--- a/2.9/generated/torch.nn.modules.rnn.GRU.html
+++ b/2.9/generated/torch.nn.modules.rnn.GRU.html
@@ -4415,7 +4415,7 @@
 <h1>GRU<a class="headerlink" href="#gru" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.GRU">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">GRU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L1165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.GRU" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">GRU</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L1165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.GRU" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a multi-layer gated recurrent unit (GRU) RNN to an input sequence.
 For each element in the input sequence, each layer computes the following
 function:</p>
diff --git a/2.9/generated/torch.nn.modules.rnn.GRUCell.html b/2.9/generated/torch.nn.modules.rnn.GRUCell.html
index 05d024cc368..8ca76fc29e8 100644
--- a/2.9/generated/torch.nn.modules.rnn.GRUCell.html
+++ b/2.9/generated/torch.nn.modules.rnn.GRUCell.html
@@ -4415,7 +4415,7 @@
 <h1>GRUCell<a class="headerlink" href="#grucell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.GRUCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">GRUCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L1721"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.GRUCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">GRUCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L1721"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.GRUCell" title="Permalink to this definition">#</a></dt>
 <dd><p>A gated recurrent unit (GRU) cell.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.16em" columnalign="left left" columnspacing="1em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>r</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>r</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>r</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>r</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>r</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>z</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>z</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>z</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>z</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>z</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>n</mi><mo>=</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>n</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>n</mi></mrow></msub><mo>+</mo><mi>r</mi><mo>⊙</mo><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>n</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>n</mi></mrow></msub><mo stretchy="false">)</mo><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><msup><mi>h</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo>=</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>z</mi><mo stretchy="false">)</mo><mo>⊙</mo><mi>n</mi><mo>+</mo><mi>z</mi><mo>⊙</mo><mi>h</mi></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{array}{ll}
diff --git a/2.9/generated/torch.nn.modules.rnn.LSTM.html b/2.9/generated/torch.nn.modules.rnn.LSTM.html
index cda8ac5e560..a083a465b32 100644
--- a/2.9/generated/torch.nn.modules.rnn.LSTM.html
+++ b/2.9/generated/torch.nn.modules.rnn.LSTM.html
@@ -4415,7 +4415,7 @@
 <h1>LSTM<a class="headerlink" href="#lstm" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.LSTM">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">LSTM</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proj_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L800"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.LSTM" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">LSTM</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proj_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L800"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.LSTM" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a multi-layer long short-term memory (LSTM) RNN to an input sequence.
 For each element in the input sequence, each layer computes the following
 function:</p>
diff --git a/2.9/generated/torch.nn.modules.rnn.LSTMCell.html b/2.9/generated/torch.nn.modules.rnn.LSTMCell.html
index 3f888c8bc21..e0dd8d4a394 100644
--- a/2.9/generated/torch.nn.modules.rnn.LSTMCell.html
+++ b/2.9/generated/torch.nn.modules.rnn.LSTMCell.html
@@ -4415,7 +4415,7 @@
 <h1>LSTMCell<a class="headerlink" href="#lstmcell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.LSTMCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">LSTMCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L1611"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.LSTMCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">LSTMCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L1611"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.LSTMCell" title="Permalink to this definition">#</a></dt>
 <dd><p>A long short-term memory (LSTM) cell.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.16em" columnalign="left left" columnspacing="1em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>i</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>i</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>i</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>i</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>i</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>f</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>f</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>f</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>f</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>f</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>g</mi><mo>=</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>g</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>g</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>g</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>g</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><mi>o</mi><mo>=</mo><mi>σ</mi><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>o</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>o</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>o</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>o</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><msup><mi>c</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo>=</mo><mi>f</mi><mo>⊙</mo><mi>c</mi><mo>+</mo><mi>i</mi><mo>⊙</mo><mi>g</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="false"><mrow><msup><mi>h</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo>=</mo><mi>o</mi><mo>⊙</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><msup><mi>c</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{array}{ll}
diff --git a/2.9/generated/torch.nn.modules.rnn.RNN.html b/2.9/generated/torch.nn.modules.rnn.RNN.html
index d6af8b47008..50a601ce068 100644
--- a/2.9/generated/torch.nn.modules.rnn.RNN.html
+++ b/2.9/generated/torch.nn.modules.rnn.RNN.html
@@ -4415,7 +4415,7 @@
 <h1>RNN<a class="headerlink" href="#rnn" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.RNN">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">RNN</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNN" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">RNN</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNN" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply a multi-layer Elman RNN with <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>tanh</mi><mo>⁡</mo></mrow><annotation encoding="application/x-tex">\tanh</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mop">tanh</span></span></span></span></span> or <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>ReLU</mtext></mrow><annotation encoding="application/x-tex">\text{ReLU}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord text"><span class="mord">ReLU</span></span></span></span></span></span>
 non-linearity to an input sequence. For each element in the input sequence,
 each layer computes the following function:</p>
@@ -4598,7 +4598,7 @@ <h1>RNN<a class="headerlink" href="#rnn" title="Permalink to this heading">#</a>
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.RNN.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">hx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L654"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNN.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">hx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L654"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNN.forward" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="torch.nn.utils.rnn.PackedSequence.html#torch.nn.utils.rnn.PackedSequence" title="torch.nn.utils.rnn.PackedSequence"><span class="pre">PackedSequence</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">hx</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="torch.nn.utils.rnn.PackedSequence.html#torch.nn.utils.rnn.PackedSequence" title="torch.nn.utils.rnn.PackedSequence"><span class="pre">torch.nn.utils.rnn.PackedSequence</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">torch.Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span></dt>
 <dd><p>Runs the forward pass.</p>
diff --git a/2.9/generated/torch.nn.modules.rnn.RNNBase.html b/2.9/generated/torch.nn.modules.rnn.RNNBase.html
index 44d302256e4..dc470f59fe4 100644
--- a/2.9/generated/torch.nn.modules.rnn.RNNBase.html
+++ b/2.9/generated/torch.nn.modules.rnn.RNNBase.html
@@ -4415,7 +4415,7 @@
 <h1>RNNBase<a class="headerlink" href="#rnnbase" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.RNNBase">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">RNNBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proj_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNNBase" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">RNNBase</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bidirectional</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">proj_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L48"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNNBase" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class for RNN modules (RNN, LSTM, GRU).</p>
 <p>Implements aspects of RNNs shared by the RNN, LSTM, and GRU classes, such as module initialization
 and utility methods for parameter storage management.</p>
@@ -4431,7 +4431,7 @@ <h1>RNNBase<a class="headerlink" href="#rnnbase" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.RNNBase.flatten_parameters">
-<span class="sig-name descname"><span class="pre">flatten_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNNBase.flatten_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">flatten_parameters</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNNBase.flatten_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset parameter data pointer so that they can use faster code paths.</p>
 <p>Right now, this works only if the module is on the GPU and cuDNN is enabled.
 Otherwise, it’s a no-op.</p>
diff --git a/2.9/generated/torch.nn.modules.rnn.RNNCell.html b/2.9/generated/torch.nn.modules.rnn.RNNCell.html
index 5bbc30ac66f..f0697223057 100644
--- a/2.9/generated/torch.nn.modules.rnn.RNNCell.html
+++ b/2.9/generated/torch.nn.modules.rnn.RNNCell.html
@@ -4415,7 +4415,7 @@
 <h1>RNNCell<a class="headerlink" href="#rnncell" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.rnn.RNNCell">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">RNNCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/rnn.py#L1492"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNNCell" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.rnn.</span></span><span class="sig-name descname"><span class="pre">RNNCell</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hidden_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tanh'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/rnn.py#L1492"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.rnn.RNNCell" title="Permalink to this definition">#</a></dt>
 <dd><p>An Elman RNN cell with tanh or ReLU non-linearity.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><msup><mi>h</mi><mo mathvariant="normal" lspace="0em" rspace="0em">′</mo></msup><mo>=</mo><mi>tanh</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>W</mi><mrow><mi>i</mi><mi>h</mi></mrow></msub><mi>x</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>i</mi><mi>h</mi></mrow></msub><mo>+</mo><msub><mi>W</mi><mrow><mi>h</mi><mi>h</mi></mrow></msub><mi>h</mi><mo>+</mo><msub><mi>b</mi><mrow><mi>h</mi><mi>h</mi></mrow></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">h&#x27; = \tanh(W_{ih} x + b_{ih}  +  W_{hh} h + b_{hh})</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8019em;"></span><span class="mord"><span class="mord mathnormal">h</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8019em;"><span style="top:-3.113em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mtight">′</span></span></span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">tanh</span><span class="mopen">(</span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">ih</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mord mathnormal">x</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8444em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal">b</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">ih</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:0.8444em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">hh</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mord mathnormal">h</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord"><span class="mord mathnormal">b</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3361em;"><span style="top:-2.55em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">hh</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span></div><p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">nonlinearity</span></code> is <cite>‘relu’</cite>, then ReLU is used in place of tanh.</p>
diff --git a/2.9/generated/torch.nn.modules.sparse.Embedding.html b/2.9/generated/torch.nn.modules.sparse.Embedding.html
index 07979b085cb..1605509e214 100644
--- a/2.9/generated/torch.nn.modules.sparse.Embedding.html
+++ b/2.9/generated/torch.nn.modules.sparse.Embedding.html
@@ -4415,7 +4415,7 @@
 <h1>Embedding<a class="headerlink" href="#embedding" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.sparse.Embedding">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.sparse.</span></span><span class="sig-name descname"><span class="pre">Embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.Embedding" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.sparse.</span></span><span class="sig-name descname"><span class="pre">Embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.Embedding" title="Permalink to this definition">#</a></dt>
 <dd><p>A simple lookup table that stores embeddings of a fixed dictionary and size.</p>
 <p>This module is often used to store word embeddings and retrieve them using indices.
 The input to the module is a list of indices, and the output is the corresponding
@@ -4523,7 +4523,7 @@ <h1>Embedding<a class="headerlink" href="#embedding" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.sparse.Embedding.from_pretrained">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_pretrained</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.Embedding.from_pretrained" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_pretrained</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L216"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.Embedding.from_pretrained" title="Permalink to this definition">#</a></dt>
 <dd><p>Create Embedding instance from given 2-dimensional FloatTensor.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.modules.sparse.EmbeddingBag.html b/2.9/generated/torch.nn.modules.sparse.EmbeddingBag.html
index 49791446272..c7d7994b061 100644
--- a/2.9/generated/torch.nn.modules.sparse.EmbeddingBag.html
+++ b/2.9/generated/torch.nn.modules.sparse.EmbeddingBag.html
@@ -4415,7 +4415,7 @@
 <h1>EmbeddingBag<a class="headerlink" href="#embeddingbag" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.sparse.EmbeddingBag">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.sparse.</span></span><span class="sig-name descname"><span class="pre">EmbeddingBag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.EmbeddingBag" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.sparse.</span></span><span class="sig-name descname"><span class="pre">EmbeddingBag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">embedding_dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_weight</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.EmbeddingBag" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute sums or means of ‘bags’ of embeddings, without instantiating the intermediate embeddings.</p>
 <p>For bags of constant length, no <code class="xref py py-attr docutils literal notranslate"><span class="pre">per_sample_weights</span></code>, no indices equal to <code class="xref py py-attr docutils literal notranslate"><span class="pre">padding_idx</span></code>,
 and with 2D inputs, this class</p>
@@ -4496,7 +4496,7 @@ <h1>EmbeddingBag<a class="headerlink" href="#embeddingbag" title="Permalink to t
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.sparse.EmbeddingBag.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offsets</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">per_sample_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.EmbeddingBag.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offsets</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">per_sample_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L429"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.EmbeddingBag.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Forward pass of EmbeddingBag.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4536,7 +4536,7 @@ <h1>EmbeddingBag<a class="headerlink" href="#embeddingbag" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.sparse.EmbeddingBag.from_pretrained">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_pretrained</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/sparse.py#L492"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.EmbeddingBag.from_pretrained" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_pretrained</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">embeddings</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">freeze</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_grad_by_freq</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'mean'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_last_offset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_idx</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/sparse.py#L492"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.sparse.EmbeddingBag.from_pretrained" title="Permalink to this definition">#</a></dt>
 <dd><p>Create EmbeddingBag instance from given 2-dimensional FloatTensor.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.modules.transformer.Transformer.html b/2.9/generated/torch.nn.modules.transformer.Transformer.html
index b49714de42c..33a97ac3f3b 100644
--- a/2.9/generated/torch.nn.modules.transformer.Transformer.html
+++ b/2.9/generated/torch.nn.modules.transformer.Transformer.html
@@ -4415,7 +4415,7 @@
 <h1>Transformer<a class="headerlink" href="#transformer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.Transformer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">Transformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model=512</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_encoder_layers=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_decoder_layers=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_encoder=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_decoder=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.Transformer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">Transformer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model=512</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead=8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_encoder_layers=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_decoder_layers=6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_encoder=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_decoder=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.Transformer" title="Permalink to this definition">#</a></dt>
 <dd><p>A basic transformer layer.</p>
 <p>This Transformer layer implements the original Transformer architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4459,7 +4459,7 @@ <h1>Transformer<a class="headerlink" href="#transformer" title="Permalink to thi
 <a class="github reference external" href="https://github.com/pytorch/examples/tree/master/word_language_model">pytorch/examples</a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.Transformer.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.Transformer.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.Transformer.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Take in and process masked source/target sequences.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4548,7 +4548,7 @@ <h1>Transformer<a class="headerlink" href="#transformer" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.Transformer.generate_square_subsequent_mask">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">generate_square_subsequent_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sz</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L292"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.Transformer.generate_square_subsequent_mask" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">generate_square_subsequent_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sz</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L292"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.Transformer.generate_square_subsequent_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Generate a square causal mask for the sequence.</p>
 <p>The masked positions are filled with float(‘-inf’). Unmasked positions are filled with float(0.0).</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.modules.transformer.TransformerDecoder.html b/2.9/generated/torch.nn.modules.transformer.TransformerDecoder.html
index 65703376420..9bcc196d9d3 100644
--- a/2.9/generated/torch.nn.modules.transformer.TransformerDecoder.html
+++ b/2.9/generated/torch.nn.modules.transformer.TransformerDecoder.html
@@ -4415,7 +4415,7 @@
 <h1>TransformerDecoder<a class="headerlink" href="#transformerdecoder" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.TransformerDecoder">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">TransformerDecoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decoder_layer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerDecoder" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">TransformerDecoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decoder_layer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L540"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerDecoder" title="Permalink to this definition">#</a></dt>
 <dd><p>TransformerDecoder is a stack of N decoder layers.</p>
 <p>This TransformerDecoder layer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4449,7 +4449,7 @@ <h1>TransformerDecoder<a class="headerlink" href="#transformerdecoder" title="Pe
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.TransformerDecoder.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerDecoder.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerDecoder.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Pass the inputs (and mask) through the decoder layer in turn.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.modules.transformer.TransformerDecoderLayer.html b/2.9/generated/torch.nn.modules.transformer.TransformerDecoderLayer.html
index b85c3f70eb6..10a01e6fa27 100644
--- a/2.9/generated/torch.nn.modules.transformer.TransformerDecoderLayer.html
+++ b/2.9/generated/torch.nn.modules.transformer.TransformerDecoderLayer.html
@@ -4415,7 +4415,7 @@
 <h1>TransformerDecoderLayer<a class="headerlink" href="#transformerdecoderlayer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.TransformerDecoderLayer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">TransformerDecoderLayer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L966"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerDecoderLayer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">TransformerDecoderLayer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L966"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerDecoderLayer" title="Permalink to this definition">#</a></dt>
 <dd><p>TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network.</p>
 <p>This TransformerDecoderLayer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4465,7 +4465,7 @@ <h1>TransformerDecoderLayer<a class="headerlink" href="#transformerdecoderlayer"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.TransformerDecoderLayer.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerDecoderLayer.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tgt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerDecoderLayer.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Pass the inputs (and mask) through the decoder layer.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.modules.transformer.TransformerEncoder.html b/2.9/generated/torch.nn.modules.transformer.TransformerEncoder.html
index 6265e0b10d9..56dff0e4300 100644
--- a/2.9/generated/torch.nn.modules.transformer.TransformerEncoder.html
+++ b/2.9/generated/torch.nn.modules.transformer.TransformerEncoder.html
@@ -4415,7 +4415,7 @@
 <h1>TransformerEncoder<a class="headerlink" href="#transformerencoder" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.TransformerEncoder">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">TransformerEncoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">encoder_layer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_nested_tensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L311"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerEncoder" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">TransformerEncoder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">encoder_layer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_layers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_nested_tensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask_check</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L311"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerEncoder" title="Permalink to this definition">#</a></dt>
 <dd><p>TransformerEncoder is a stack of N encoder layers.</p>
 <p>This TransformerEncoder layer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4451,7 +4451,7 @@ <h1>TransformerEncoder<a class="headerlink" href="#transformerencoder" title="Pe
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.TransformerEncoder.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerEncoder.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerEncoder.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Pass the input through the encoder layers in turn.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.modules.transformer.TransformerEncoderLayer.html b/2.9/generated/torch.nn.modules.transformer.TransformerEncoderLayer.html
index cb9ea667573..f07419bc80f 100644
--- a/2.9/generated/torch.nn.modules.transformer.TransformerEncoderLayer.html
+++ b/2.9/generated/torch.nn.modules.transformer.TransformerEncoderLayer.html
@@ -4415,7 +4415,7 @@
 <h1>TransformerEncoderLayer<a class="headerlink" href="#transformerencoderlayer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.TransformerEncoderLayer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">TransformerEncoderLayer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L645"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerEncoderLayer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.transformer.</span></span><span class="sig-name descname"><span class="pre">TransformerEncoderLayer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d_model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nhead</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim_feedforward=2048</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dropout=0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activation=&lt;function</span> <span class="pre">relu&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layer_norm_eps=1e-05</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_first=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bias=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype=None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L645"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerEncoderLayer" title="Permalink to this definition">#</a></dt>
 <dd><p>TransformerEncoderLayer is made up of self-attn and feedforward network.</p>
 <p>This TransformerEncoderLayer implements the original architecture described
 in the <a class="reference external" href="https://arxiv.org/abs/1706.03762">Attention Is All You Need</a> paper. The
@@ -4495,7 +4495,7 @@ <h1>TransformerEncoderLayer<a class="headerlink" href="#transformerencoderlayer"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.transformer.TransformerEncoderLayer.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/transformer.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerEncoderLayer.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src_key_padding_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/transformer.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.transformer.TransformerEncoderLayer.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Pass the input through the encoder layer.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.modules.upsampling.Upsample.html b/2.9/generated/torch.nn.modules.upsampling.Upsample.html
index 80d124c42dc..63e14f7ed72 100644
--- a/2.9/generated/torch.nn.modules.upsampling.Upsample.html
+++ b/2.9/generated/torch.nn.modules.upsampling.Upsample.html
@@ -4415,7 +4415,7 @@
 <h1>Upsample<a class="headerlink" href="#upsample" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.upsampling.Upsample">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.upsampling.</span></span><span class="sig-name descname"><span class="pre">Upsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompute_scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.Upsample" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.upsampling.</span></span><span class="sig-name descname"><span class="pre">Upsample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'nearest'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_corners</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recompute_scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.Upsample" title="Permalink to this definition">#</a></dt>
 <dd><p>Upsamples a given multi-channel 1D (temporal), 2D (spatial) or 3D (volumetric) data.</p>
 <p>The input data is assumed to be of the form
 <cite>minibatch x channels x [optional depth] x [optional height] x width</cite>.
@@ -4540,7 +4540,7 @@ <h1>Upsample<a class="headerlink" href="#upsample" title="Permalink to this head
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.upsampling.Upsample.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.Upsample.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.Upsample.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4551,7 +4551,7 @@ <h1>Upsample<a class="headerlink" href="#upsample" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.modules.upsampling.Upsample.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.Upsample.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.Upsample.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Runs the forward pass.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.nn.modules.upsampling.UpsamplingBilinear2d.html b/2.9/generated/torch.nn.modules.upsampling.UpsamplingBilinear2d.html
index f060b5c866f..810e3d1cd20 100644
--- a/2.9/generated/torch.nn.modules.upsampling.UpsamplingBilinear2d.html
+++ b/2.9/generated/torch.nn.modules.upsampling.UpsamplingBilinear2d.html
@@ -4415,7 +4415,7 @@
 <h1>UpsamplingBilinear2d<a class="headerlink" href="#upsamplingbilinear2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.upsampling.UpsamplingBilinear2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.upsampling.</span></span><span class="sig-name descname"><span class="pre">UpsamplingBilinear2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.UpsamplingBilinear2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.upsampling.</span></span><span class="sig-name descname"><span class="pre">UpsamplingBilinear2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L251"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.UpsamplingBilinear2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D bilinear upsampling to an input signal composed of several input channels.</p>
 <p>To specify the scale, it takes either the <code class="xref py py-attr docutils literal notranslate"><span class="pre">size</span></code> or the <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale_factor</span></code>
 as it’s constructor argument.</p>
diff --git a/2.9/generated/torch.nn.modules.upsampling.UpsamplingNearest2d.html b/2.9/generated/torch.nn.modules.upsampling.UpsamplingNearest2d.html
index 75482bb9b74..861828e1540 100644
--- a/2.9/generated/torch.nn.modules.upsampling.UpsamplingNearest2d.html
+++ b/2.9/generated/torch.nn.modules.upsampling.UpsamplingNearest2d.html
@@ -4415,7 +4415,7 @@
 <h1>UpsamplingNearest2d<a class="headerlink" href="#upsamplingnearest2d" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.modules.upsampling.UpsamplingNearest2d">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.upsampling.</span></span><span class="sig-name descname"><span class="pre">UpsamplingNearest2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/upsampling.py#L202"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.UpsamplingNearest2d" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.modules.upsampling.</span></span><span class="sig-name descname"><span class="pre">UpsamplingNearest2d</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/upsampling.py#L202"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.modules.upsampling.UpsamplingNearest2d" title="Permalink to this definition">#</a></dt>
 <dd><p>Applies a 2D nearest neighbor upsampling to an input signal composed of several input channels.</p>
 <p>To specify the scale, it takes either the <code class="xref py py-attr docutils literal notranslate"><span class="pre">size</span></code> or the <code class="xref py py-attr docutils literal notranslate"><span class="pre">scale_factor</span></code>
 as it’s constructor argument.</p>
diff --git a/2.9/generated/torch.nn.parallel.DistributedDataParallel.html b/2.9/generated/torch.nn.parallel.DistributedDataParallel.html
index 9b4b0356d16..7bae2b2568d 100644
--- a/2.9/generated/torch.nn.parallel.DistributedDataParallel.html
+++ b/2.9/generated/torch.nn.parallel.DistributedDataParallel.html
@@ -4404,7 +4404,7 @@
 <h1>DistributedDataParallel<a class="headerlink" href="#distributeddataparallel" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.parallel.DistributedDataParallel">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parallel.</span></span><span class="sig-name descname"><span class="pre">DistributedDataParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">broadcast_buffers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_sync</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket_cap_mb</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">find_unused_parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gradient_as_bucket_view</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">static_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delay_all_reduce_named_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param_to_hook_all_reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mixed_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_all_reduce_unused_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/distributed.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parallel.</span></span><span class="sig-name descname"><span class="pre">DistributedDataParallel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">broadcast_buffers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_sync</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">process_group</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket_cap_mb</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">find_unused_parameters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_reduction</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gradient_as_bucket_view</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">static_graph</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">delay_all_reduce_named_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param_to_hook_all_reduce</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mixed_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_mesh</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_all_reduce_unused_params</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/distributed.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel" title="Permalink to this definition">#</a></dt>
 <dd><p>Implement distributed data parallelism based on <code class="docutils literal notranslate"><span class="pre">torch.distributed</span></code> at module level.</p>
 <p>This container provides data parallelism by synchronizing gradients
 across each model replica. The devices to synchronize across are
@@ -4744,7 +4744,7 @@ <h1>DistributedDataParallel<a class="headerlink" href="#distributeddataparallel"
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.parallel.DistributedDataParallel.join">
-<span class="sig-name descname"><span class="pre">join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">divide_by_initial_world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">throw_on_early_termination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/distributed.py#L1760"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel.join" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">divide_by_initial_world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">throw_on_early_termination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/distributed.py#L1760"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel.join" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager for training with uneven inputs across processes in DDP.</p>
 <p>This context manager will keep track of already-joined DDP processes,
 and “shadow” the forward and backward passes by inserting collective
@@ -4840,7 +4840,7 @@ <h1>DistributedDataParallel<a class="headerlink" href="#distributeddataparallel"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.parallel.DistributedDataParallel.join_hook">
-<span class="sig-name descname"><span class="pre">join_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/distributed.py#L1866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel.join_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">join_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/distributed.py#L1866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel.join_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>DDP join hook enables training on uneven inputs by mirroring communications in forward and backward passes.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4869,7 +4869,7 @@ <h1>DistributedDataParallel<a class="headerlink" href="#distributeddataparallel"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.parallel.DistributedDataParallel.no_sync">
-<span class="sig-name descname"><span class="pre">no_sync</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/distributed.py#L1436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel.no_sync" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">no_sync</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/distributed.py#L1436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel.no_sync" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager to disable gradient synchronizations across DDP processes.</p>
 <p>Within this context, gradients will be accumulated on module
 variables, which will later be synchronized in the first
@@ -4891,7 +4891,7 @@ <h1>DistributedDataParallel<a class="headerlink" href="#distributeddataparallel"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.parallel.DistributedDataParallel.register_comm_hook">
-<span class="sig-name descname"><span class="pre">register_comm_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parallel/distributed.py#L1948"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel.register_comm_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_comm_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parallel/distributed.py#L1948"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parallel.DistributedDataParallel.register_comm_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register communication hook for user-defined DDP aggregation of gradients across multiple workers.</p>
 <p>This hook would be very useful for researchers to try out new ideas. For
 example, this hook can be used to implement several algorithms like GossipGrad
diff --git a/2.9/generated/torch.nn.parameter.Buffer.html b/2.9/generated/torch.nn.parameter.Buffer.html
index 794789c438f..2c07dbf9248 100644
--- a/2.9/generated/torch.nn.parameter.Buffer.html
+++ b/2.9/generated/torch.nn.parameter.Buffer.html
@@ -4404,7 +4404,7 @@
 <h1>Buffer<a class="headerlink" href="#buffer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.parameter.Buffer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">Buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parameter.py#L242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.Buffer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">Buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parameter.py#L242"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.Buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>A kind of Tensor that should not be considered a model
 parameter. For example, BatchNorm’s <code class="docutils literal notranslate"><span class="pre">running_mean</span></code> is not a parameter, but is part of the module’s state.</p>
 <p>Buffers are <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> subclasses, that have a
diff --git a/2.9/generated/torch.nn.parameter.Parameter.html b/2.9/generated/torch.nn.parameter.Parameter.html
index c4bfb982c6d..15e60e7c05d 100644
--- a/2.9/generated/torch.nn.parameter.Parameter.html
+++ b/2.9/generated/torch.nn.parameter.Parameter.html
@@ -4404,7 +4404,7 @@
 <h1>Parameter<a class="headerlink" href="#parameter" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.parameter.Parameter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">Parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parameter.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.Parameter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">Parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parameter.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.Parameter" title="Permalink to this definition">#</a></dt>
 <dd><p>A kind of Tensor that is to be considered a module parameter.</p>
 <p>Parameters are <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">Tensor</span></code></a> subclasses, that have a
 very special property when used with <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> s - when they’re
diff --git a/2.9/generated/torch.nn.parameter.UninitializedBuffer.html b/2.9/generated/torch.nn.parameter.UninitializedBuffer.html
index 591230c2627..2f705366c3b 100644
--- a/2.9/generated/torch.nn.parameter.UninitializedBuffer.html
+++ b/2.9/generated/torch.nn.parameter.UninitializedBuffer.html
@@ -4404,7 +4404,7 @@
 <h1>UninitializedBuffer<a class="headerlink" href="#uninitializedbuffer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.parameter.UninitializedBuffer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">UninitializedBuffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parameter.py#L271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.UninitializedBuffer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">UninitializedBuffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parameter.py#L271"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.UninitializedBuffer" title="Permalink to this definition">#</a></dt>
 <dd><p>A buffer that is not initialized.</p>
 <p>Uninitialized Buffer is a a special case of <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a>
 where the shape of the data is still unknown.</p>
diff --git a/2.9/generated/torch.nn.parameter.UninitializedParameter.html b/2.9/generated/torch.nn.parameter.UninitializedParameter.html
index 370a4583fc1..a1541f91ee1 100644
--- a/2.9/generated/torch.nn.parameter.UninitializedParameter.html
+++ b/2.9/generated/torch.nn.parameter.UninitializedParameter.html
@@ -4404,7 +4404,7 @@
 <h1>UninitializedParameter<a class="headerlink" href="#uninitializedparameter" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.parameter.UninitializedParameter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">UninitializedParameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parameter.py#L198"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.UninitializedParameter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">UninitializedParameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parameter.py#L198"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.UninitializedParameter" title="Permalink to this definition">#</a></dt>
 <dd><p>A parameter that is not initialized.</p>
 <p>Uninitialized Parameters are a special case of <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Parameter</span></code>
 where the shape of the data is still unknown.</p>
@@ -4419,7 +4419,7 @@ <h1>UninitializedParameter<a class="headerlink" href="#uninitializedparameter" t
 </dl>
 <dl class="py attribute">
 <dt class="sig sig-object py" id="torch.nn.parameter.UninitializedParameter.cls_to_become">
-<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parameter.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.UninitializedParameter.cls_to_become" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cls_to_become</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parameter.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.UninitializedParameter.cls_to_become" title="Permalink to this definition">#</a></dt>
 <dd><p>alias of <a class="reference internal" href="torch.nn.parameter.Parameter.html#torch.nn.parameter.Parameter" title="torch.nn.parameter.Parameter"><code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code></a></p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.nn.parameter.is_lazy.html b/2.9/generated/torch.nn.parameter.is_lazy.html
index 00424d97c04..b5527ad77d8 100644
--- a/2.9/generated/torch.nn.parameter.is_lazy.html
+++ b/2.9/generated/torch.nn.parameter.is_lazy.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.parameter.is_lazy<a class="headerlink" href="#torch-nn-parameter-is-lazy" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.parameter.is_lazy">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">is_lazy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/parameter.py#L188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.is_lazy" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.parameter.</span></span><span class="sig-name descname"><span class="pre">is_lazy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/parameter.py#L188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.parameter.is_lazy" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether <code class="docutils literal notranslate"><span class="pre">param</span></code> is an <code class="docutils literal notranslate"><span class="pre">UninitializedParameter</span></code> or <code class="docutils literal notranslate"><span class="pre">UninitializedBuffer</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm.html b/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm.html
index 9edaa333a16..8d4ed4f7345 100644
--- a/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm.html
+++ b/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.clip_grad.clip_grad_norm<a class="headerlink" href="#torch-nn-utils-clip-grad-clip-grad-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.clip_grad.clip_grad_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.clip_grad.</span></span><span class="sig-name descname"><span class="pre">clip_grad_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/clip_grad.py#L236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad.clip_grad_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.clip_grad.</span></span><span class="sig-name descname"><span class="pre">clip_grad_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/clip_grad.py#L236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad.clip_grad_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Clip the gradient norm of an iterable of parameters.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm_.html b/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm_.html
index ba0b103d56f..7734f7a9b77 100644
--- a/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm_.html
+++ b/2.9/generated/torch.nn.utils.clip_grad.clip_grad_norm_.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.clip_grad.clip_grad_norm_<a class="headerlink" href="#torch-nn-utils-clip-grad-clip-grad-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.clip_grad.clip_grad_norm_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.clip_grad.</span></span><span class="sig-name descname"><span class="pre">clip_grad_norm_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/clip_grad.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad.clip_grad_norm_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.clip_grad.</span></span><span class="sig-name descname"><span class="pre">clip_grad_norm_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/clip_grad.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad.clip_grad_norm_" title="Permalink to this definition">#</a></dt>
 <dd><p>Clip the gradient norm of an iterable of parameters.</p>
 <p>The norm is computed over the norms of the individual gradients of all parameters,
 as if the norms of the individual gradients were concatenated into a single vector.
diff --git a/2.9/generated/torch.nn.utils.clip_grad.clip_grad_value_.html b/2.9/generated/torch.nn.utils.clip_grad.clip_grad_value_.html
index 4607c68bcce..f58924b3d2b 100644
--- a/2.9/generated/torch.nn.utils.clip_grad.clip_grad_value_.html
+++ b/2.9/generated/torch.nn.utils.clip_grad.clip_grad_value_.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.clip_grad.clip_grad_value_<a class="headerlink" href="#torch-nn-utils-clip-grad-clip-grad-value" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.clip_grad.clip_grad_value_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.clip_grad.</span></span><span class="sig-name descname"><span class="pre">clip_grad_value_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">clip_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/clip_grad.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad.clip_grad_value_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.clip_grad.</span></span><span class="sig-name descname"><span class="pre">clip_grad_value_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">clip_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/clip_grad.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad.clip_grad_value_" title="Permalink to this definition">#</a></dt>
 <dd><p>Clip the gradients of an iterable of parameters at specified value.</p>
 <p>Gradients are modified in-place.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.utils.clip_grad_norm.html b/2.9/generated/torch.nn.utils.clip_grad_norm.html
index 2e5aa227946..4ae113dca55 100644
--- a/2.9/generated/torch.nn.utils.clip_grad_norm.html
+++ b/2.9/generated/torch.nn.utils.clip_grad_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.clip_grad_norm<a class="headerlink" href="#torch-nn-utils-clip-grad-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.clip_grad_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">clip_grad_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/clip_grad.py#L236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">clip_grad_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/clip_grad.py#L236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Clip the gradient norm of an iterable of parameters.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.utils.clip_grad_norm_.html b/2.9/generated/torch.nn.utils.clip_grad_norm_.html
index 1c0134c4bdb..feb28052b56 100644
--- a/2.9/generated/torch.nn.utils.clip_grad_norm_.html
+++ b/2.9/generated/torch.nn.utils.clip_grad_norm_.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.clip_grad_norm_<a class="headerlink" href="#torch-nn-utils-clip-grad-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.clip_grad_norm_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">clip_grad_norm_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/clip_grad.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad_norm_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">clip_grad_norm_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/clip_grad.py#L185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad_norm_" title="Permalink to this definition">#</a></dt>
 <dd><p>Clip the gradient norm of an iterable of parameters.</p>
 <p>The norm is computed over the norms of the individual gradients of all parameters,
 as if the norms of the individual gradients were concatenated into a single vector.
diff --git a/2.9/generated/torch.nn.utils.clip_grad_value_.html b/2.9/generated/torch.nn.utils.clip_grad_value_.html
index f5e5718e8b2..f8d83342e2c 100644
--- a/2.9/generated/torch.nn.utils.clip_grad_value_.html
+++ b/2.9/generated/torch.nn.utils.clip_grad_value_.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.clip_grad_value_<a class="headerlink" href="#torch-nn-utils-clip-grad-value" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.clip_grad_value_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">clip_grad_value_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">clip_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/clip_grad.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad_value_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">clip_grad_value_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">clip_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/clip_grad.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grad_value_" title="Permalink to this definition">#</a></dt>
 <dd><p>Clip the gradients of an iterable of parameters at specified value.</p>
 <p>Gradients are modified in-place.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.nn.utils.clip_grads_with_norm_.html b/2.9/generated/torch.nn.utils.clip_grads_with_norm_.html
index d8d4f5f2fad..8edcf6e0843 100644
--- a/2.9/generated/torch.nn.utils.clip_grads_with_norm_.html
+++ b/2.9/generated/torch.nn.utils.clip_grads_with_norm_.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.clip_grads_with_norm_<a class="headerlink" href="#torch-nn-utils-clip-grads-with-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.clip_grads_with_norm_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">clip_grads_with_norm_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/clip_grad.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grads_with_norm_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">clip_grads_with_norm_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_norm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/clip_grad.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.clip_grads_with_norm_" title="Permalink to this definition">#</a></dt>
 <dd><p>Scale the gradients of an iterable of parameters given a pre-calculated total norm and desired max norm.</p>
 <p>The gradients will be scaled by the following calculation</p>
 <div class="math">
diff --git a/2.9/generated/torch.nn.utils.convert_conv2d_weight_memory_format.html b/2.9/generated/torch.nn.utils.convert_conv2d_weight_memory_format.html
index 34ec112563d..5a2204bdea9 100644
--- a/2.9/generated/torch.nn.utils.convert_conv2d_weight_memory_format.html
+++ b/2.9/generated/torch.nn.utils.convert_conv2d_weight_memory_format.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.convert_conv2d_weight_memory_format<a class="headerlink" href="#torch-nn-utils-convert-conv2d-weight-memory-format" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.convert_conv2d_weight_memory_format">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">convert_conv2d_weight_memory_format</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/memory_format.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.convert_conv2d_weight_memory_format" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">convert_conv2d_weight_memory_format</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/memory_format.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.convert_conv2d_weight_memory_format" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert <code class="docutils literal notranslate"><span class="pre">memory_format</span></code> of <code class="docutils literal notranslate"><span class="pre">nn.Conv2d.weight</span></code> to <code class="docutils literal notranslate"><span class="pre">memory_format</span></code>.</p>
 <p>The conversion recursively applies to nested <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code>, including <code class="docutils literal notranslate"><span class="pre">module</span></code>.
 Note that it only changes the memory_format, but not the semantics of each dimensions.
diff --git a/2.9/generated/torch.nn.utils.convert_conv3d_weight_memory_format.html b/2.9/generated/torch.nn.utils.convert_conv3d_weight_memory_format.html
index 34f9f8ec348..e96373b13f1 100644
--- a/2.9/generated/torch.nn.utils.convert_conv3d_weight_memory_format.html
+++ b/2.9/generated/torch.nn.utils.convert_conv3d_weight_memory_format.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.convert_conv3d_weight_memory_format<a class="headerlink" href="#torch-nn-utils-convert-conv3d-weight-memory-format" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.convert_conv3d_weight_memory_format">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">convert_conv3d_weight_memory_format</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/memory_format.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.convert_conv3d_weight_memory_format" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">convert_conv3d_weight_memory_format</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/memory_format.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.convert_conv3d_weight_memory_format" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert <code class="docutils literal notranslate"><span class="pre">memory_format</span></code> of <code class="docutils literal notranslate"><span class="pre">nn.Conv3d.weight</span></code> to <code class="docutils literal notranslate"><span class="pre">memory_format</span></code>
 The conversion recursively applies to nested <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code>, including <code class="docutils literal notranslate"><span class="pre">module</span></code>.
 Note that it only changes the memory_format, but not the semantics of each dimensions.
diff --git a/2.9/generated/torch.nn.utils.convert_parameters.parameters_to_vector.html b/2.9/generated/torch.nn.utils.convert_parameters.parameters_to_vector.html
index 2f11f7fc760..cce3c58d363 100644
--- a/2.9/generated/torch.nn.utils.convert_parameters.parameters_to_vector.html
+++ b/2.9/generated/torch.nn.utils.convert_parameters.parameters_to_vector.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.convert_parameters.parameters_to_vector<a class="headerlink" href="#torch-nn-utils-convert-parameters-parameters-to-vector" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.convert_parameters.parameters_to_vector">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.convert_parameters.</span></span><span class="sig-name descname"><span class="pre">parameters_to_vector</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/convert_parameters.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.convert_parameters.parameters_to_vector" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.convert_parameters.</span></span><span class="sig-name descname"><span class="pre">parameters_to_vector</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/convert_parameters.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.convert_parameters.parameters_to_vector" title="Permalink to this definition">#</a></dt>
 <dd><p>Flatten an iterable of parameters into a single vector.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.convert_parameters.vector_to_parameters.html b/2.9/generated/torch.nn.utils.convert_parameters.vector_to_parameters.html
index 29511e27123..d88aea02e4b 100644
--- a/2.9/generated/torch.nn.utils.convert_parameters.vector_to_parameters.html
+++ b/2.9/generated/torch.nn.utils.convert_parameters.vector_to_parameters.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.convert_parameters.vector_to_parameters<a class="headerlink" href="#torch-nn-utils-convert-parameters-vector-to-parameters" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.convert_parameters.vector_to_parameters">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.convert_parameters.</span></span><span class="sig-name descname"><span class="pre">vector_to_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/convert_parameters.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.convert_parameters.vector_to_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.convert_parameters.</span></span><span class="sig-name descname"><span class="pre">vector_to_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/convert_parameters.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.convert_parameters.vector_to_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy slices of a vector into an iterable of parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.fuse_conv_bn_eval.html b/2.9/generated/torch.nn.utils.fuse_conv_bn_eval.html
index 152313bd6ac..3b8e1adec9b 100644
--- a/2.9/generated/torch.nn.utils.fuse_conv_bn_eval.html
+++ b/2.9/generated/torch.nn.utils.fuse_conv_bn_eval.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.fuse_conv_bn_eval<a class="headerlink" href="#torch-nn-utils-fuse-conv-bn-eval" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.fuse_conv_bn_eval">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">fuse_conv_bn_eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transpose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/fusion.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fuse_conv_bn_eval" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">fuse_conv_bn_eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transpose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/fusion.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fuse_conv_bn_eval" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse a convolutional module and a BatchNorm module into a single, new convolutional module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.fuse_conv_bn_weights.html b/2.9/generated/torch.nn.utils.fuse_conv_bn_weights.html
index 7a4254cb405..862c81c5850 100644
--- a/2.9/generated/torch.nn.utils.fuse_conv_bn_weights.html
+++ b/2.9/generated/torch.nn.utils.fuse_conv_bn_weights.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.fuse_conv_bn_weights<a class="headerlink" href="#torch-nn-utils-fuse-conv-bn-weights" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.fuse_conv_bn_weights">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">fuse_conv_bn_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transpose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/fusion.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fuse_conv_bn_weights" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">fuse_conv_bn_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transpose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/fusion.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fuse_conv_bn_weights" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse convolutional module parameters and BatchNorm module parameters into new convolutional module parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.fuse_linear_bn_eval.html b/2.9/generated/torch.nn.utils.fuse_linear_bn_eval.html
index c80d2c63f48..d9d0a4c5744 100644
--- a/2.9/generated/torch.nn.utils.fuse_linear_bn_eval.html
+++ b/2.9/generated/torch.nn.utils.fuse_linear_bn_eval.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.fuse_linear_bn_eval<a class="headerlink" href="#torch-nn-utils-fuse-linear-bn-eval" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.fuse_linear_bn_eval">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">fuse_linear_bn_eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/fusion.py#L109"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fuse_linear_bn_eval" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">fuse_linear_bn_eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/fusion.py#L109"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fuse_linear_bn_eval" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse a linear module and a BatchNorm module into a single, new linear module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.fuse_linear_bn_weights.html b/2.9/generated/torch.nn.utils.fuse_linear_bn_weights.html
index 392fb583de2..618b98f26e8 100644
--- a/2.9/generated/torch.nn.utils.fuse_linear_bn_weights.html
+++ b/2.9/generated/torch.nn.utils.fuse_linear_bn_weights.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.fuse_linear_bn_weights<a class="headerlink" href="#torch-nn-utils-fuse-linear-bn-weights" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.fuse_linear_bn_weights">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">fuse_linear_bn_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">linear_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/fusion.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fuse_linear_bn_weights" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">fuse_linear_bn_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">linear_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/fusion.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fuse_linear_bn_weights" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse linear module parameters and BatchNorm module parameters into new linear module parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.fusion.fuse_conv_bn_eval.html b/2.9/generated/torch.nn.utils.fusion.fuse_conv_bn_eval.html
index 875782f11a1..973abd80a50 100644
--- a/2.9/generated/torch.nn.utils.fusion.fuse_conv_bn_eval.html
+++ b/2.9/generated/torch.nn.utils.fusion.fuse_conv_bn_eval.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.fusion.fuse_conv_bn_eval<a class="headerlink" href="#torch-nn-utils-fusion-fuse-conv-bn-eval" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.fusion.fuse_conv_bn_eval">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.fusion.</span></span><span class="sig-name descname"><span class="pre">fuse_conv_bn_eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transpose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/fusion.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fusion.fuse_conv_bn_eval" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.fusion.</span></span><span class="sig-name descname"><span class="pre">fuse_conv_bn_eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transpose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/fusion.py#L20"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fusion.fuse_conv_bn_eval" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse a convolutional module and a BatchNorm module into a single, new convolutional module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.fusion.fuse_conv_bn_weights.html b/2.9/generated/torch.nn.utils.fusion.fuse_conv_bn_weights.html
index 93227ec5481..d3da2ef0017 100644
--- a/2.9/generated/torch.nn.utils.fusion.fuse_conv_bn_weights.html
+++ b/2.9/generated/torch.nn.utils.fusion.fuse_conv_bn_weights.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.fusion.fuse_conv_bn_weights<a class="headerlink" href="#torch-nn-utils-fusion-fuse-conv-bn-weights" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.fusion.fuse_conv_bn_weights">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.fusion.</span></span><span class="sig-name descname"><span class="pre">fuse_conv_bn_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transpose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/fusion.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fusion.fuse_conv_bn_weights" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.fusion.</span></span><span class="sig-name descname"><span class="pre">fuse_conv_bn_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">conv_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conv_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transpose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/fusion.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fusion.fuse_conv_bn_weights" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse convolutional module parameters and BatchNorm module parameters into new convolutional module parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.fusion.fuse_linear_bn_eval.html b/2.9/generated/torch.nn.utils.fusion.fuse_linear_bn_eval.html
index 3991b0f735f..855a1945f7f 100644
--- a/2.9/generated/torch.nn.utils.fusion.fuse_linear_bn_eval.html
+++ b/2.9/generated/torch.nn.utils.fusion.fuse_linear_bn_eval.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.fusion.fuse_linear_bn_eval<a class="headerlink" href="#torch-nn-utils-fusion-fuse-linear-bn-eval" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.fusion.fuse_linear_bn_eval">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.fusion.</span></span><span class="sig-name descname"><span class="pre">fuse_linear_bn_eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/fusion.py#L109"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fusion.fuse_linear_bn_eval" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.fusion.</span></span><span class="sig-name descname"><span class="pre">fuse_linear_bn_eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/fusion.py#L109"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fusion.fuse_linear_bn_eval" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse a linear module and a BatchNorm module into a single, new linear module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.fusion.fuse_linear_bn_weights.html b/2.9/generated/torch.nn.utils.fusion.fuse_linear_bn_weights.html
index 1f0efbbcd96..95ad4aa1bd5 100644
--- a/2.9/generated/torch.nn.utils.fusion.fuse_linear_bn_weights.html
+++ b/2.9/generated/torch.nn.utils.fusion.fuse_linear_bn_weights.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.fusion.fuse_linear_bn_weights<a class="headerlink" href="#torch-nn-utils-fusion-fuse-linear-bn-weights" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.fusion.fuse_linear_bn_weights">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.fusion.</span></span><span class="sig-name descname"><span class="pre">fuse_linear_bn_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">linear_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/fusion.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fusion.fuse_linear_bn_weights" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.fusion.</span></span><span class="sig-name descname"><span class="pre">fuse_linear_bn_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">linear_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">linear_b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rm</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_rv</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_w</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bn_b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/fusion.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.fusion.fuse_linear_bn_weights" title="Permalink to this definition">#</a></dt>
 <dd><p>Fuse linear module parameters and BatchNorm module parameters into new linear module parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.get_total_norm.html b/2.9/generated/torch.nn.utils.get_total_norm.html
index a9f3c5f2c59..8df10aed1d7 100644
--- a/2.9/generated/torch.nn.utils.get_total_norm.html
+++ b/2.9/generated/torch.nn.utils.get_total_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.get_total_norm<a class="headerlink" href="#torch-nn-utils-get-total-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.get_total_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">get_total_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/clip_grad.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.get_total_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">get_total_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensors</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">error_if_nonfinite</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/clip_grad.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.get_total_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the norm of an iterable of tensors.</p>
 <p>The norm is computed over the norms of the individual tensors, as if the norms of
 the individual tensors were concatenated into a single vector.</p>
diff --git a/2.9/generated/torch.nn.utils.init.skip_init.html b/2.9/generated/torch.nn.utils.init.skip_init.html
index 43515ad1d45..35a929746fc 100644
--- a/2.9/generated/torch.nn.utils.init.skip_init.html
+++ b/2.9/generated/torch.nn.utils.init.skip_init.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.init.skip_init<a class="headerlink" href="#torch-nn-utils-init-skip-init" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.init.skip_init">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.init.</span></span><span class="sig-name descname"><span class="pre">skip_init</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_cls</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/init.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.init.skip_init" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.init.</span></span><span class="sig-name descname"><span class="pre">skip_init</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_cls</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/init.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.init.skip_init" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a module class object and args / kwargs, instantiate the module without initializing parameters / buffers.</p>
 <p>This can be useful if initialization is slow or if custom initialization will
 be performed, making the default initialization unnecessary. There are some caveats to this, due to
diff --git a/2.9/generated/torch.nn.utils.memory_format.convert_conv2d_weight_memory_format.html b/2.9/generated/torch.nn.utils.memory_format.convert_conv2d_weight_memory_format.html
index 86d2e3e4a35..2da0bde2fb1 100644
--- a/2.9/generated/torch.nn.utils.memory_format.convert_conv2d_weight_memory_format.html
+++ b/2.9/generated/torch.nn.utils.memory_format.convert_conv2d_weight_memory_format.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.memory_format.convert_conv2d_weight_memory_format<a class="headerlink" href="#torch-nn-utils-memory-format-convert-conv2d-weight-memory-format" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.memory_format.convert_conv2d_weight_memory_format">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.memory_format.</span></span><span class="sig-name descname"><span class="pre">convert_conv2d_weight_memory_format</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/memory_format.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.memory_format.convert_conv2d_weight_memory_format" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.memory_format.</span></span><span class="sig-name descname"><span class="pre">convert_conv2d_weight_memory_format</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/memory_format.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.memory_format.convert_conv2d_weight_memory_format" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert <code class="docutils literal notranslate"><span class="pre">memory_format</span></code> of <code class="docutils literal notranslate"><span class="pre">nn.Conv2d.weight</span></code> to <code class="docutils literal notranslate"><span class="pre">memory_format</span></code>.</p>
 <p>The conversion recursively applies to nested <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code>, including <code class="docutils literal notranslate"><span class="pre">module</span></code>.
 Note that it only changes the memory_format, but not the semantics of each dimensions.
diff --git a/2.9/generated/torch.nn.utils.memory_format.convert_conv3d_weight_memory_format.html b/2.9/generated/torch.nn.utils.memory_format.convert_conv3d_weight_memory_format.html
index 239542a57bd..647a9f89184 100644
--- a/2.9/generated/torch.nn.utils.memory_format.convert_conv3d_weight_memory_format.html
+++ b/2.9/generated/torch.nn.utils.memory_format.convert_conv3d_weight_memory_format.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.memory_format.convert_conv3d_weight_memory_format<a class="headerlink" href="#torch-nn-utils-memory-format-convert-conv3d-weight-memory-format" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.memory_format.convert_conv3d_weight_memory_format">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.memory_format.</span></span><span class="sig-name descname"><span class="pre">convert_conv3d_weight_memory_format</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/memory_format.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.memory_format.convert_conv3d_weight_memory_format" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.memory_format.</span></span><span class="sig-name descname"><span class="pre">convert_conv3d_weight_memory_format</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/memory_format.py#L90"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.memory_format.convert_conv3d_weight_memory_format" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert <code class="docutils literal notranslate"><span class="pre">memory_format</span></code> of <code class="docutils literal notranslate"><span class="pre">nn.Conv3d.weight</span></code> to <code class="docutils literal notranslate"><span class="pre">memory_format</span></code>
 The conversion recursively applies to nested <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code>, including <code class="docutils literal notranslate"><span class="pre">module</span></code>.
 Note that it only changes the memory_format, but not the semantics of each dimensions.
diff --git a/2.9/generated/torch.nn.utils.parameters_to_vector.html b/2.9/generated/torch.nn.utils.parameters_to_vector.html
index 1873af6f852..642270973bd 100644
--- a/2.9/generated/torch.nn.utils.parameters_to_vector.html
+++ b/2.9/generated/torch.nn.utils.parameters_to_vector.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parameters_to_vector<a class="headerlink" href="#torch-nn-utils-parameters-to-vector" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parameters_to_vector">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">parameters_to_vector</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/convert_parameters.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parameters_to_vector" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">parameters_to_vector</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/convert_parameters.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parameters_to_vector" title="Permalink to this definition">#</a></dt>
 <dd><p>Flatten an iterable of parameters into a single vector.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.parametrizations.orthogonal.html b/2.9/generated/torch.nn.utils.parametrizations.orthogonal.html
index eba2225f5cd..c0392a500c7 100644
--- a/2.9/generated/torch.nn.utils.parametrizations.orthogonal.html
+++ b/2.9/generated/torch.nn.utils.parametrizations.orthogonal.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrizations.orthogonal<a class="headerlink" href="#torch-nn-utils-parametrizations-orthogonal" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrizations.orthogonal">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrizations.</span></span><span class="sig-name descname"><span class="pre">orthogonal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">orthogonal_map</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_trivialization</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrizations.py#L191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrizations.orthogonal" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrizations.</span></span><span class="sig-name descname"><span class="pre">orthogonal</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">orthogonal_map</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_trivialization</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrizations.py#L191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrizations.orthogonal" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply an orthogonal or unitary parametrization to a matrix or a batch of matrices.</p>
 <p>Letting <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="double-struck">K</mi></mrow><annotation encoding="application/x-tex">\mathbb{K}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6889em;"></span><span class="mord mathbb">K</span></span></span></span></span> be <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="double-struck">R</mi></mrow><annotation encoding="application/x-tex">\mathbb{R}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6889em;"></span><span class="mord mathbb">R</span></span></span></span></span> or <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="double-struck">C</mi></mrow><annotation encoding="application/x-tex">\mathbb{C}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6889em;"></span><span class="mord mathbb">C</span></span></span></span></span>, the parametrized
 matrix <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>Q</mi><mo>∈</mo><msup><mi mathvariant="double-struck">K</mi><mrow><mi>m</mi><mo>×</mo><mi>n</mi></mrow></msup></mrow><annotation encoding="application/x-tex">Q \in \mathbb{K}^{m \times n}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8778em;vertical-align:-0.1944em;"></span><span class="mord mathnormal">Q</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">∈</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:0.7713em;"></span><span class="mord"><span class="mord mathbb">K</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.7713em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">m</span><span class="mbin mtight">×</span><span class="mord mathnormal mtight">n</span></span></span></span></span></span></span></span></span></span></span></span></span> is <strong>orthogonal</strong> as</p>
diff --git a/2.9/generated/torch.nn.utils.parametrizations.spectral_norm.html b/2.9/generated/torch.nn.utils.parametrizations.spectral_norm.html
index c7cf0e63304..6a9582fb116 100644
--- a/2.9/generated/torch.nn.utils.parametrizations.spectral_norm.html
+++ b/2.9/generated/torch.nn.utils.parametrizations.spectral_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrizations.spectral_norm<a class="headerlink" href="#torch-nn-utils-parametrizations-spectral-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrizations.spectral_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrizations.</span></span><span class="sig-name descname"><span class="pre">spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_power_iterations</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrizations.py#L527"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrizations.spectral_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrizations.</span></span><span class="sig-name descname"><span class="pre">spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_power_iterations</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrizations.py#L527"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrizations.spectral_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply spectral normalization to a parameter in the given module.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><msub><mi mathvariant="bold">W</mi><mrow><mi>S</mi><mi>N</mi></mrow></msub><mo>=</mo><mfrac><mi mathvariant="bold">W</mi><mrow><mi>σ</mi><mo stretchy="false">(</mo><mi mathvariant="bold">W</mi><mo stretchy="false">)</mo></mrow></mfrac><mo separator="true">,</mo><mi>σ</mi><mo stretchy="false">(</mo><mi mathvariant="bold">W</mi><mo stretchy="false">)</mo><mo>=</mo><munder><mrow><mi>max</mi><mo>⁡</mo></mrow><mrow><mi mathvariant="bold">h</mi><mo>:</mo><mi mathvariant="bold">h</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></munder><mfrac><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">W</mi><mi mathvariant="bold">h</mi><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub></mrow><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">h</mi><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub></mrow></mfrac></mrow><annotation encoding="application/x-tex">\mathbf{W}_{SN} = \dfrac{\mathbf{W}}{\sigma(\mathbf{W})},
diff --git a/2.9/generated/torch.nn.utils.parametrizations.weight_norm.html b/2.9/generated/torch.nn.utils.parametrizations.weight_norm.html
index 4e5eda508ec..e44b4c1bceb 100644
--- a/2.9/generated/torch.nn.utils.parametrizations.weight_norm.html
+++ b/2.9/generated/torch.nn.utils.parametrizations.weight_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrizations.weight_norm<a class="headerlink" href="#torch-nn-utils-parametrizations-weight-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrizations.weight_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrizations.</span></span><span class="sig-name descname"><span class="pre">weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrizations.py#L334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrizations.weight_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrizations.</span></span><span class="sig-name descname"><span class="pre">weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrizations.py#L334"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrizations.weight_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply weight normalization to a parameter in the given module.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mi mathvariant="bold">w</mi><mo>=</mo><mi>g</mi><mfrac><mi mathvariant="bold">v</mi><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">v</mi><mi mathvariant="normal">∥</mi></mrow></mfrac></mrow><annotation encoding="application/x-tex">\mathbf{w} = g \dfrac{\mathbf{v}}{\|\mathbf{v}\|}
diff --git a/2.9/generated/torch.nn.utils.parametrize.ParametrizationList.html b/2.9/generated/torch.nn.utils.parametrize.ParametrizationList.html
index 6e8cc67c36b..0cd7f8f1191 100644
--- a/2.9/generated/torch.nn.utils.parametrize.ParametrizationList.html
+++ b/2.9/generated/torch.nn.utils.parametrize.ParametrizationList.html
@@ -4404,7 +4404,7 @@
 <h1>ParametrizationList<a class="headerlink" href="#parametrizationlist" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrize.ParametrizationList">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">ParametrizationList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">original</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unsafe</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrize.py#L94"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.ParametrizationList" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">ParametrizationList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modules</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">original</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unsafe</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrize.py#L94"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.ParametrizationList" title="Permalink to this definition">#</a></dt>
 <dd><p>A sequential container that holds and manages the original parameters or buffers of a parametrized <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module" title="torch.nn.Module"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.Module</span></code></a>.</p>
 <p>It is the type of <code class="docutils literal notranslate"><span class="pre">module.parametrizations[tensor_name]</span></code> when <code class="docutils literal notranslate"><span class="pre">module[tensor_name]</span></code>
 has been parametrized with <a class="reference internal" href="torch.nn.utils.parametrize.register_parametrization.html#torch.nn.utils.parametrize.register_parametrization" title="torch.nn.utils.parametrize.register_parametrization"><code class="xref py py-func docutils literal notranslate"><span class="pre">register_parametrization()</span></code></a>.</p>
@@ -4432,7 +4432,7 @@ <h1>ParametrizationList<a class="headerlink" href="#parametrizationlist" title="
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrize.ParametrizationList.right_inverse">
-<span class="sig-name descname"><span class="pre">right_inverse</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrize.py#L232"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.ParametrizationList.right_inverse" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">right_inverse</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrize.py#L232"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.ParametrizationList.right_inverse" title="Permalink to this definition">#</a></dt>
 <dd><p>Call the <code class="docutils literal notranslate"><span class="pre">right_inverse</span></code> methods of the parametrizations in the inverse registration order.</p>
 <p>Then, it stores the result in <code class="docutils literal notranslate"><span class="pre">self.original</span></code> if <code class="docutils literal notranslate"><span class="pre">right_inverse</span></code> outputs one tensor
 or in <code class="docutils literal notranslate"><span class="pre">self.original0</span></code>, <code class="docutils literal notranslate"><span class="pre">self.original1</span></code>, … if it outputs several.</p>
diff --git a/2.9/generated/torch.nn.utils.parametrize.cached.html b/2.9/generated/torch.nn.utils.parametrize.cached.html
index 26092e1e36c..4f3084504c8 100644
--- a/2.9/generated/torch.nn.utils.parametrize.cached.html
+++ b/2.9/generated/torch.nn.utils.parametrize.cached.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrize.cached<a class="headerlink" href="#torch-nn-utils-parametrize-cached" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrize.cached">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">cached</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrize.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.cached" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">cached</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrize.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.cached" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager that enables the caching system within parametrizations registered with <a class="reference internal" href="torch.nn.utils.parametrize.register_parametrization.html#torch.nn.utils.parametrize.register_parametrization" title="torch.nn.utils.parametrize.register_parametrization"><code class="xref py py-func docutils literal notranslate"><span class="pre">register_parametrization()</span></code></a>.</p>
 <p>The value of the parametrized objects is computed and cached the first time
 they are required when this context manager is active. The cached values are
diff --git a/2.9/generated/torch.nn.utils.parametrize.is_parametrized.html b/2.9/generated/torch.nn.utils.parametrize.is_parametrized.html
index 94af1eb4a2b..25b864fff82 100644
--- a/2.9/generated/torch.nn.utils.parametrize.is_parametrized.html
+++ b/2.9/generated/torch.nn.utils.parametrize.is_parametrized.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrize.is_parametrized<a class="headerlink" href="#torch-nn-utils-parametrize-is-parametrized" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrize.is_parametrized">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">is_parametrized</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrize.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.is_parametrized" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">is_parametrized</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrize.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.is_parametrized" title="Permalink to this definition">#</a></dt>
 <dd><p>Determine if a module has a parametrization.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.parametrize.register_parametrization.html b/2.9/generated/torch.nn.utils.parametrize.register_parametrization.html
index 25396abe8d8..e92089aed90 100644
--- a/2.9/generated/torch.nn.utils.parametrize.register_parametrization.html
+++ b/2.9/generated/torch.nn.utils.parametrize.register_parametrization.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrize.register_parametrization<a class="headerlink" href="#torch-nn-utils-parametrize-register-parametrization" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrize.register_parametrization">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">register_parametrization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parametrization</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unsafe</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrize.py#L417"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.register_parametrization" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">register_parametrization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parametrization</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unsafe</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrize.py#L417"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.register_parametrization" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a parametrization to a tensor in a module.</p>
 <p>Assume that <code class="docutils literal notranslate"><span class="pre">tensor_name=&quot;weight&quot;</span></code> for simplicity. When accessing <code class="docutils literal notranslate"><span class="pre">module.weight</span></code>,
 the module will return the parametrized version <code class="docutils literal notranslate"><span class="pre">parametrization(module.weight)</span></code>.
diff --git a/2.9/generated/torch.nn.utils.parametrize.remove_parametrizations.html b/2.9/generated/torch.nn.utils.parametrize.remove_parametrizations.html
index beb829a337f..01e1c789271 100644
--- a/2.9/generated/torch.nn.utils.parametrize.remove_parametrizations.html
+++ b/2.9/generated/torch.nn.utils.parametrize.remove_parametrizations.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrize.remove_parametrizations<a class="headerlink" href="#torch-nn-utils-parametrize-remove-parametrizations" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrize.remove_parametrizations">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">remove_parametrizations</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">leave_parametrized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrize.py#L655"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.remove_parametrizations" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">remove_parametrizations</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">leave_parametrized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrize.py#L655"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.remove_parametrizations" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the parametrizations on a tensor in a module.</p>
 <ul class="simple">
 <li><p>If <code class="docutils literal notranslate"><span class="pre">leave_parametrized=True</span></code>, <code class="docutils literal notranslate"><span class="pre">module[tensor_name]</span></code> will be set to
diff --git a/2.9/generated/torch.nn.utils.parametrize.transfer_parametrizations_and_params.html b/2.9/generated/torch.nn.utils.parametrize.transfer_parametrizations_and_params.html
index 87ee2cdbd26..6df053a78bc 100644
--- a/2.9/generated/torch.nn.utils.parametrize.transfer_parametrizations_and_params.html
+++ b/2.9/generated/torch.nn.utils.parametrize.transfer_parametrizations_and_params.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrize.transfer_parametrizations_and_params<a class="headerlink" href="#torch-nn-utils-parametrize-transfer-parametrizations-and-params" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrize.transfer_parametrizations_and_params">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">transfer_parametrizations_and_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">from_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">to_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrize.py#L761"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.transfer_parametrizations_and_params" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">transfer_parametrizations_and_params</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">from_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">to_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrize.py#L761"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.transfer_parametrizations_and_params" title="Permalink to this definition">#</a></dt>
 <dd><p>Transfer parametrizations and the parameters they parametrize from <code class="xref py py-attr docutils literal notranslate"><span class="pre">from_module</span></code> to <code class="xref py py-attr docutils literal notranslate"><span class="pre">to_module</span></code>.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">tensor_name</span></code> is specified, only transfers the specified parameter, otherwise
 transfers all parametrized parameters. If those parameters do not exist in to_module, it will create them.
diff --git a/2.9/generated/torch.nn.utils.parametrize.type_before_parametrizations.html b/2.9/generated/torch.nn.utils.parametrize.type_before_parametrizations.html
index 24b091d9e32..4e66352d840 100644
--- a/2.9/generated/torch.nn.utils.parametrize.type_before_parametrizations.html
+++ b/2.9/generated/torch.nn.utils.parametrize.type_before_parametrizations.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.parametrize.type_before_parametrizations<a class="headerlink" href="#torch-nn-utils-parametrize-type-before-parametrizations" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.parametrize.type_before_parametrizations">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">type_before_parametrizations</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/parametrize.py#L749"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.type_before_parametrizations" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.parametrize.</span></span><span class="sig-name descname"><span class="pre">type_before_parametrizations</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/parametrize.py#L749"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.parametrize.type_before_parametrizations" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the module type before parametrizations were applied and if not, then it returns the module type.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.prune.BasePruningMethod.html b/2.9/generated/torch.nn.utils.prune.BasePruningMethod.html
index d6aeade2dbd..32eaa13679e 100644
--- a/2.9/generated/torch.nn.utils.prune.BasePruningMethod.html
+++ b/2.9/generated/torch.nn.utils.prune.BasePruningMethod.html
@@ -4404,13 +4404,13 @@
 <h1>BasePruningMethod<a class="headerlink" href="#basepruningmethod" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.BasePruningMethod">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">BasePruningMethod</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">BasePruningMethod</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod" title="Permalink to this definition">#</a></dt>
 <dd><p>Abstract base class for creation of new pruning techniques.</p>
 <p>Provides a skeleton for customization requiring the overriding of methods
 such as <a class="reference internal" href="#torch.nn.utils.prune.BasePruningMethod.compute_mask" title="torch.nn.utils.prune.BasePruningMethod.compute_mask"><code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code></a> and <a class="reference internal" href="#torch.nn.utils.prune.BasePruningMethod.apply" title="torch.nn.utils.prune.BasePruningMethod.apply"><code class="xref py py-meth docutils literal notranslate"><span class="pre">apply()</span></code></a>.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.BasePruningMethod.apply">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.apply" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Add pruning on the fly and reparametrization of a tensor.</p>
 <p>Adds the forward pre-hook that enables pruning on the fly and
 the reparametrization of a tensor in terms of the original tensor
@@ -4437,7 +4437,7 @@ <h1>BasePruningMethod<a class="headerlink" href="#basepruningmethod" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.BasePruningMethod.apply_mask">
-<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.apply_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.apply_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Simply handles the multiplication between the parameter being pruned and the generated mask.</p>
 <p>Fetches the mask and the original tensor from the module
 and returns the pruned version of the tensor.</p>
@@ -4456,7 +4456,7 @@ <h1>BasePruningMethod<a class="headerlink" href="#basepruningmethod" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.BasePruningMethod.compute_mask">
-<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">compute_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.compute_mask" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">compute_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.compute_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a mask for the input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>Starting from a base <code class="docutils literal notranslate"><span class="pre">default_mask</span></code> (which should be a mask of ones
 if the tensor has not been pruned yet), generate a random mask to
@@ -4484,7 +4484,7 @@ <h1>BasePruningMethod<a class="headerlink" href="#basepruningmethod" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.BasePruningMethod.prune">
-<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.prune" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.prune" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a pruned version of input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>According to the pruning rule specified in <a class="reference internal" href="#torch.nn.utils.prune.BasePruningMethod.compute_mask" title="torch.nn.utils.prune.BasePruningMethod.compute_mask"><code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4511,7 +4511,7 @@ <h1>BasePruningMethod<a class="headerlink" href="#basepruningmethod" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.BasePruningMethod.remove">
-<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.BasePruningMethod.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned,
 and the parameter named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list.
diff --git a/2.9/generated/torch.nn.utils.prune.CustomFromMask.html b/2.9/generated/torch.nn.utils.prune.CustomFromMask.html
index be62482c644..1a4c670dcb2 100644
--- a/2.9/generated/torch.nn.utils.prune.CustomFromMask.html
+++ b/2.9/generated/torch.nn.utils.prune.CustomFromMask.html
@@ -4404,10 +4404,10 @@
 <h1>CustomFromMask<a class="headerlink" href="#customfrommask" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.CustomFromMask">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">CustomFromMask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L796"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">CustomFromMask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L796"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask" title="Permalink to this definition">#</a></dt>
 <dd><dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.CustomFromMask.apply">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask.apply" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L807"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Add pruning on the fly and reparametrization of a tensor.</p>
 <p>Adds the forward pre-hook that enables pruning on the fly and
 the reparametrization of a tensor in terms of the original tensor
@@ -4425,7 +4425,7 @@ <h1>CustomFromMask<a class="headerlink" href="#customfrommask" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.CustomFromMask.apply_mask">
-<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask.apply_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask.apply_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Simply handles the multiplication between the parameter being pruned and the generated mask.</p>
 <p>Fetches the mask and the original tensor from the module
 and returns the pruned version of the tensor.</p>
@@ -4444,7 +4444,7 @@ <h1>CustomFromMask<a class="headerlink" href="#customfrommask" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.CustomFromMask.prune">
-<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask.prune" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask.prune" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a pruned version of input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>According to the pruning rule specified in <code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code>.</p>
 <dl class="field-list simple">
@@ -4471,7 +4471,7 @@ <h1>CustomFromMask<a class="headerlink" href="#customfrommask" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.CustomFromMask.remove">
-<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.CustomFromMask.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned,
 and the parameter named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list.
diff --git a/2.9/generated/torch.nn.utils.prune.Identity.html b/2.9/generated/torch.nn.utils.prune.Identity.html
index a047fffe477..c6e23bf5b8a 100644
--- a/2.9/generated/torch.nn.utils.prune.Identity.html
+++ b/2.9/generated/torch.nn.utils.prune.Identity.html
@@ -4404,11 +4404,11 @@
 <h1>Identity<a class="headerlink" href="#identity" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.Identity">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">Identity</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">Identity</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity" title="Permalink to this definition">#</a></dt>
 <dd><p>Utility pruning method that does not prune any units but generates the pruning parametrization with a mask of ones.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.Identity.apply">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity.apply" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Add pruning on the fly and reparametrization of a tensor.</p>
 <p>Adds the forward pre-hook that enables pruning on the fly and
 the reparametrization of a tensor in terms of the original tensor
@@ -4426,7 +4426,7 @@ <h1>Identity<a class="headerlink" href="#identity" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.Identity.apply_mask">
-<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity.apply_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity.apply_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Simply handles the multiplication between the parameter being pruned and the generated mask.</p>
 <p>Fetches the mask and the original tensor from the module
 and returns the pruned version of the tensor.</p>
@@ -4445,7 +4445,7 @@ <h1>Identity<a class="headerlink" href="#identity" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.Identity.prune">
-<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity.prune" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity.prune" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a pruned version of input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>According to the pruning rule specified in <code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code>.</p>
 <dl class="field-list simple">
@@ -4472,7 +4472,7 @@ <h1>Identity<a class="headerlink" href="#identity" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.Identity.remove">
-<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.Identity.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned,
 and the parameter named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list.
diff --git a/2.9/generated/torch.nn.utils.prune.L1Unstructured.html b/2.9/generated/torch.nn.utils.prune.L1Unstructured.html
index 1063690a3ab..f94954c4828 100644
--- a/2.9/generated/torch.nn.utils.prune.L1Unstructured.html
+++ b/2.9/generated/torch.nn.utils.prune.L1Unstructured.html
@@ -4404,7 +4404,7 @@
 <h1>L1Unstructured<a class="headerlink" href="#l1unstructured" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.L1Unstructured">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">L1Unstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">amount</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L494"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">L1Unstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">amount</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L494"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune (currently unpruned) units in a tensor by zeroing out the ones with the lowest L1-norm.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4416,7 +4416,7 @@ <h1>L1Unstructured<a class="headerlink" href="#l1unstructured" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.L1Unstructured.apply">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L533"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured.apply" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L533"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Add pruning on the fly and reparametrization of a tensor.</p>
 <p>Adds the forward pre-hook that enables pruning on the fly and
 the reparametrization of a tensor in terms of the original tensor
@@ -4443,7 +4443,7 @@ <h1>L1Unstructured<a class="headerlink" href="#l1unstructured" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.L1Unstructured.apply_mask">
-<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured.apply_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured.apply_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Simply handles the multiplication between the parameter being pruned and the generated mask.</p>
 <p>Fetches the mask and the original tensor from the module
 and returns the pruned version of the tensor.</p>
@@ -4462,7 +4462,7 @@ <h1>L1Unstructured<a class="headerlink" href="#l1unstructured" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.L1Unstructured.prune">
-<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured.prune" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured.prune" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a pruned version of input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>According to the pruning rule specified in <code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code>.</p>
 <dl class="field-list simple">
@@ -4489,7 +4489,7 @@ <h1>L1Unstructured<a class="headerlink" href="#l1unstructured" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.L1Unstructured.remove">
-<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.L1Unstructured.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned,
 and the parameter named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list.
diff --git a/2.9/generated/torch.nn.utils.prune.LnStructured.html b/2.9/generated/torch.nn.utils.prune.LnStructured.html
index 4659b170e16..be7c7f27b9e 100644
--- a/2.9/generated/torch.nn.utils.prune.LnStructured.html
+++ b/2.9/generated/torch.nn.utils.prune.LnStructured.html
@@ -4404,7 +4404,7 @@
 <h1>LnStructured<a class="headerlink" href="#lnstructured" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.LnStructured">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">LnStructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">LnStructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L666"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune entire (currently unpruned) channels in a tensor based on their L<code class="docutils literal notranslate"><span class="pre">n</span></code>-norm.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4422,7 +4422,7 @@ <h1>LnStructured<a class="headerlink" href="#lnstructured" title="Permalink to t
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.LnStructured.apply">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L760"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.apply" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L760"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Add pruning on the fly and reparametrization of a tensor.</p>
 <p>Adds the forward pre-hook that enables pruning on the fly and
 the reparametrization of a tensor in terms of the original tensor
@@ -4453,7 +4453,7 @@ <h1>LnStructured<a class="headerlink" href="#lnstructured" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.LnStructured.apply_mask">
-<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.apply_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.apply_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Simply handles the multiplication between the parameter being pruned and the generated mask.</p>
 <p>Fetches the mask and the original tensor from the module
 and returns the pruned version of the tensor.</p>
@@ -4472,7 +4472,7 @@ <h1>LnStructured<a class="headerlink" href="#lnstructured" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.LnStructured.compute_mask">
-<span class="sig-name descname"><span class="pre">compute_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L689"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.compute_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">compute_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L689"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.compute_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a mask for the input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>Starting from a base <code class="docutils literal notranslate"><span class="pre">default_mask</span></code> (which should be a mask of ones
 if the tensor has not been pruned yet), generate a mask to apply on
@@ -4501,7 +4501,7 @@ <h1>LnStructured<a class="headerlink" href="#lnstructured" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.LnStructured.prune">
-<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.prune" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.prune" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a pruned version of input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>According to the pruning rule specified in <a class="reference internal" href="#torch.nn.utils.prune.LnStructured.compute_mask" title="torch.nn.utils.prune.LnStructured.compute_mask"><code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4528,7 +4528,7 @@ <h1>LnStructured<a class="headerlink" href="#lnstructured" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.LnStructured.remove">
-<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.LnStructured.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned,
 and the parameter named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list.
diff --git a/2.9/generated/torch.nn.utils.prune.PruningContainer.html b/2.9/generated/torch.nn.utils.prune.PruningContainer.html
index 1f38198a0f5..c31bdfd9f2e 100644
--- a/2.9/generated/torch.nn.utils.prune.PruningContainer.html
+++ b/2.9/generated/torch.nn.utils.prune.PruningContainer.html
@@ -4404,7 +4404,7 @@
 <h1>PruningContainer<a class="headerlink" href="#pruningcontainer" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.PruningContainer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">PruningContainer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L262"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">PruningContainer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L262"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer" title="Permalink to this definition">#</a></dt>
 <dd><p>Container holding a sequence of pruning methods for iterative pruning.</p>
 <p>Keeps track of the order in which pruning methods are applied and handles
 combining successive pruning calls.</p>
@@ -4412,7 +4412,7 @@ <h1>PruningContainer<a class="headerlink" href="#pruningcontainer" title="Permal
 them.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.PruningContainer.add_pruning_method">
-<span class="sig-name descname"><span class="pre">add_pruning_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">method</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L284"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.add_pruning_method" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_pruning_method</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">method</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L284"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.add_pruning_method" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a child pruning <code class="docutils literal notranslate"><span class="pre">method</span></code> to the container.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4424,7 +4424,7 @@ <h1>PruningContainer<a class="headerlink" href="#pruningcontainer" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.PruningContainer.apply">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.apply" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Add pruning on the fly and reparametrization of a tensor.</p>
 <p>Adds the forward pre-hook that enables pruning on the fly and
 the reparametrization of a tensor in terms of the original tensor
@@ -4451,7 +4451,7 @@ <h1>PruningContainer<a class="headerlink" href="#pruningcontainer" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.PruningContainer.apply_mask">
-<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.apply_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.apply_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Simply handles the multiplication between the parameter being pruned and the generated mask.</p>
 <p>Fetches the mask and the original tensor from the module
 and returns the pruned version of the tensor.</p>
@@ -4470,7 +4470,7 @@ <h1>PruningContainer<a class="headerlink" href="#pruningcontainer" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.PruningContainer.compute_mask">
-<span class="sig-name descname"><span class="pre">compute_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L312"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.compute_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">compute_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L312"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.compute_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply the latest <code class="docutils literal notranslate"><span class="pre">method</span></code> by computing the new partial masks and returning its combination with the <code class="docutils literal notranslate"><span class="pre">default_mask</span></code>.</p>
 <p>The new partial mask should be computed on the entries or channels
 that were not zeroed out by the <code class="docutils literal notranslate"><span class="pre">default_mask</span></code>.
@@ -4505,7 +4505,7 @@ <h1>PruningContainer<a class="headerlink" href="#pruningcontainer" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.PruningContainer.prune">
-<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.prune" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.prune" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a pruned version of input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>According to the pruning rule specified in <a class="reference internal" href="#torch.nn.utils.prune.PruningContainer.compute_mask" title="torch.nn.utils.prune.PruningContainer.compute_mask"><code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4532,7 +4532,7 @@ <h1>PruningContainer<a class="headerlink" href="#pruningcontainer" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.PruningContainer.remove">
-<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.PruningContainer.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned,
 and the parameter named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list.
diff --git a/2.9/generated/torch.nn.utils.prune.RandomStructured.html b/2.9/generated/torch.nn.utils.prune.RandomStructured.html
index dbaf4bd0c2b..f55e4945d59 100644
--- a/2.9/generated/torch.nn.utils.prune.RandomStructured.html
+++ b/2.9/generated/torch.nn.utils.prune.RandomStructured.html
@@ -4404,7 +4404,7 @@
 <h1>RandomStructured<a class="headerlink" href="#randomstructured" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomStructured">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">RandomStructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L560"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">RandomStructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L560"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune entire (currently unpruned) channels in a tensor at random.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4420,7 +4420,7 @@ <h1>RandomStructured<a class="headerlink" href="#randomstructured" title="Permal
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomStructured.apply">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L644"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.apply" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L644"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Add pruning on the fly and reparametrization of a tensor.</p>
 <p>Adds the forward pre-hook that enables pruning on the fly and
 the reparametrization of a tensor in terms of the original tensor
@@ -4444,7 +4444,7 @@ <h1>RandomStructured<a class="headerlink" href="#randomstructured" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomStructured.apply_mask">
-<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.apply_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.apply_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Simply handles the multiplication between the parameter being pruned and the generated mask.</p>
 <p>Fetches the mask and the original tensor from the module
 and returns the pruned version of the tensor.</p>
@@ -4463,7 +4463,7 @@ <h1>RandomStructured<a class="headerlink" href="#randomstructured" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomStructured.compute_mask">
-<span class="sig-name descname"><span class="pre">compute_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.compute_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">compute_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.compute_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a mask for the input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>Starting from a base <code class="docutils literal notranslate"><span class="pre">default_mask</span></code> (which should be a mask of ones
 if the tensor has not been pruned yet), generate a random mask to
@@ -4492,7 +4492,7 @@ <h1>RandomStructured<a class="headerlink" href="#randomstructured" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomStructured.prune">
-<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.prune" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.prune" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a pruned version of input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>According to the pruning rule specified in <a class="reference internal" href="#torch.nn.utils.prune.RandomStructured.compute_mask" title="torch.nn.utils.prune.RandomStructured.compute_mask"><code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -4519,7 +4519,7 @@ <h1>RandomStructured<a class="headerlink" href="#randomstructured" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomStructured.remove">
-<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomStructured.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned,
 and the parameter named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list.
diff --git a/2.9/generated/torch.nn.utils.prune.RandomUnstructured.html b/2.9/generated/torch.nn.utils.prune.RandomUnstructured.html
index 216705dee84..70dec03c27b 100644
--- a/2.9/generated/torch.nn.utils.prune.RandomUnstructured.html
+++ b/2.9/generated/torch.nn.utils.prune.RandomUnstructured.html
@@ -4404,7 +4404,7 @@
 <h1>RandomUnstructured<a class="headerlink" href="#randomunstructured" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomUnstructured">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">RandomUnstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">amount</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L435"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">RandomUnstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">amount</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L435"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune (currently unpruned) units in a tensor at random.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4420,7 +4420,7 @@ <h1>RandomUnstructured<a class="headerlink" href="#randomunstructured" title="Pe
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomUnstructured.apply">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L474"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured.apply" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L474"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Add pruning on the fly and reparametrization of a tensor.</p>
 <p>Adds the forward pre-hook that enables pruning on the fly and
 the reparametrization of a tensor in terms of the original tensor
@@ -4442,7 +4442,7 @@ <h1>RandomUnstructured<a class="headerlink" href="#randomunstructured" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomUnstructured.apply_mask">
-<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured.apply_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L53"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured.apply_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Simply handles the multiplication between the parameter being pruned and the generated mask.</p>
 <p>Fetches the mask and the original tensor from the module
 and returns the pruned version of the tensor.</p>
@@ -4461,7 +4461,7 @@ <h1>RandomUnstructured<a class="headerlink" href="#randomunstructured" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomUnstructured.prune">
-<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured.prune" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">prune</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured.prune" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute and returns a pruned version of input tensor <code class="docutils literal notranslate"><span class="pre">t</span></code>.</p>
 <p>According to the pruning rule specified in <code class="xref py py-meth docutils literal notranslate"><span class="pre">compute_mask()</span></code>.</p>
 <dl class="field-list simple">
@@ -4488,7 +4488,7 @@ <h1>RandomUnstructured<a class="headerlink" href="#randomunstructured" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.RandomUnstructured.remove">
-<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.RandomUnstructured.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned,
 and the parameter named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list.
diff --git a/2.9/generated/torch.nn.utils.prune.custom_from_mask.html b/2.9/generated/torch.nn.utils.prune.custom_from_mask.html
index 825ae9890a0..610bb8aac1a 100644
--- a/2.9/generated/torch.nn.utils.prune.custom_from_mask.html
+++ b/2.9/generated/torch.nn.utils.prune.custom_from_mask.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.custom_from_mask<a class="headerlink" href="#torch-nn-utils-prune-custom-from-mask" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.custom_from_mask">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">custom_from_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L1148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.custom_from_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">custom_from_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L1148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.custom_from_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune tensor corresponding to parameter called <code class="docutils literal notranslate"><span class="pre">name</span></code> in <code class="docutils literal notranslate"><span class="pre">module</span></code> by applying the pre-computed mask in <code class="docutils literal notranslate"><span class="pre">mask</span></code>.</p>
 <p>Modifies module in place (and also return the modified module) by:</p>
 <ol class="arabic simple">
diff --git a/2.9/generated/torch.nn.utils.prune.global_unstructured.html b/2.9/generated/torch.nn.utils.prune.global_unstructured.html
index 457d8f02326..f779e67655a 100644
--- a/2.9/generated/torch.nn.utils.prune.global_unstructured.html
+++ b/2.9/generated/torch.nn.utils.prune.global_unstructured.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.global_unstructured<a class="headerlink" href="#torch-nn-utils-prune-global-unstructured" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.global_unstructured">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">global_unstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pruning_method</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L1025"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.global_unstructured" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">global_unstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pruning_method</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L1025"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.global_unstructured" title="Permalink to this definition">#</a></dt>
 <dd><p>Globally prunes tensors corresponding to all parameters in <code class="docutils literal notranslate"><span class="pre">parameters</span></code> by applying the specified <code class="docutils literal notranslate"><span class="pre">pruning_method</span></code>.</p>
 <p>Modifies modules in place by:</p>
 <ol class="arabic simple">
diff --git a/2.9/generated/torch.nn.utils.prune.identity.html b/2.9/generated/torch.nn.utils.prune.identity.html
index e20f5c4edde..6dbc09b3b53 100644
--- a/2.9/generated/torch.nn.utils.prune.identity.html
+++ b/2.9/generated/torch.nn.utils.prune.identity.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.identity<a class="headerlink" href="#torch-nn-utils-prune-identity" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.identity">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">identity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.identity" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">identity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.identity" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply pruning reparametrization without pruning any units.</p>
 <p>Applies pruning reparametrization to the tensor corresponding to the
 parameter called <code class="docutils literal notranslate"><span class="pre">name</span></code> in <code class="docutils literal notranslate"><span class="pre">module</span></code> without actually pruning any
diff --git a/2.9/generated/torch.nn.utils.prune.is_pruned.html b/2.9/generated/torch.nn.utils.prune.is_pruned.html
index 0f452be6ffe..60c5f327dab 100644
--- a/2.9/generated/torch.nn.utils.prune.is_pruned.html
+++ b/2.9/generated/torch.nn.utils.prune.is_pruned.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.is_pruned<a class="headerlink" href="#torch-nn-utils-prune-is-pruned" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.is_pruned">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">is_pruned</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L1211"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.is_pruned" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">is_pruned</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L1211"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.is_pruned" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if a module is pruned by looking for pruning pre-hooks.</p>
 <p>Check whether <code class="docutils literal notranslate"><span class="pre">module</span></code> is pruned by looking for
 <code class="docutils literal notranslate"><span class="pre">forward_pre_hooks</span></code> in its modules that inherit from the
diff --git a/2.9/generated/torch.nn.utils.prune.l1_unstructured.html b/2.9/generated/torch.nn.utils.prune.l1_unstructured.html
index a1057fae0e3..bc47a481b65 100644
--- a/2.9/generated/torch.nn.utils.prune.l1_unstructured.html
+++ b/2.9/generated/torch.nn.utils.prune.l1_unstructured.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.l1_unstructured<a class="headerlink" href="#torch-nn-utils-prune-l1-unstructured" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.l1_unstructured">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">l1_unstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L895"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.l1_unstructured" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">l1_unstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L895"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.l1_unstructured" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune tensor by removing units with the lowest L1-norm.</p>
 <p>Prunes tensor corresponding to parameter called <code class="docutils literal notranslate"><span class="pre">name</span></code> in <code class="docutils literal notranslate"><span class="pre">module</span></code>
 by removing the specified <cite>amount</cite> of (currently unpruned) units with the
diff --git a/2.9/generated/torch.nn.utils.prune.ln_structured.html b/2.9/generated/torch.nn.utils.prune.ln_structured.html
index 67c9fcb77dd..5562fb8bb34 100644
--- a/2.9/generated/torch.nn.utils.prune.ln_structured.html
+++ b/2.9/generated/torch.nn.utils.prune.ln_structured.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.ln_structured<a class="headerlink" href="#torch-nn-utils-prune-ln-structured" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.ln_structured">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">ln_structured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L978"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.ln_structured" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">ln_structured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importance_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L978"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.ln_structured" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune tensor by removing channels with the lowest L<code class="docutils literal notranslate"><span class="pre">n</span></code>-norm along the specified dimension.</p>
 <p>Prunes tensor corresponding to parameter called <code class="docutils literal notranslate"><span class="pre">name</span></code> in <code class="docutils literal notranslate"><span class="pre">module</span></code>
 by removing the specified <code class="docutils literal notranslate"><span class="pre">amount</span></code> of (currently unpruned) channels
diff --git a/2.9/generated/torch.nn.utils.prune.random_structured.html b/2.9/generated/torch.nn.utils.prune.random_structured.html
index 0e6c3aacef7..6dc275a37da 100644
--- a/2.9/generated/torch.nn.utils.prune.random_structured.html
+++ b/2.9/generated/torch.nn.utils.prune.random_structured.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.random_structured<a class="headerlink" href="#torch-nn-utils-prune-random-structured" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.random_structured">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">random_structured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L939"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.random_structured" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">random_structured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L939"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.random_structured" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune tensor by removing random channels along the specified dimension.</p>
 <p>Prunes tensor corresponding to parameter called <code class="docutils literal notranslate"><span class="pre">name</span></code> in <code class="docutils literal notranslate"><span class="pre">module</span></code>
 by removing the specified <code class="docutils literal notranslate"><span class="pre">amount</span></code> of (currently unpruned) channels
diff --git a/2.9/generated/torch.nn.utils.prune.random_unstructured.html b/2.9/generated/torch.nn.utils.prune.random_unstructured.html
index 99b417b223a..dc531018c0c 100644
--- a/2.9/generated/torch.nn.utils.prune.random_unstructured.html
+++ b/2.9/generated/torch.nn.utils.prune.random_unstructured.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.random_unstructured<a class="headerlink" href="#torch-nn-utils-prune-random-unstructured" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.random_unstructured">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">random_unstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L858"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.random_unstructured" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">random_unstructured</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amount</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L858"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.random_unstructured" title="Permalink to this definition">#</a></dt>
 <dd><p>Prune tensor by removing random (currently unpruned) units.</p>
 <p>Prunes tensor corresponding to parameter called <code class="docutils literal notranslate"><span class="pre">name</span></code> in <code class="docutils literal notranslate"><span class="pre">module</span></code>
 by removing the specified <code class="docutils literal notranslate"><span class="pre">amount</span></code> of (currently unpruned) units
diff --git a/2.9/generated/torch.nn.utils.prune.remove.html b/2.9/generated/torch.nn.utils.prune.remove.html
index 6bc965a733a..8695b4b3275 100644
--- a/2.9/generated/torch.nn.utils.prune.remove.html
+++ b/2.9/generated/torch.nn.utils.prune.remove.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.prune.remove<a class="headerlink" href="#torch-nn-utils-prune-remove" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.prune.remove">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/prune.py#L1181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.remove" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.prune.</span></span><span class="sig-name descname"><span class="pre">remove</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/prune.py#L1181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.prune.remove" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the pruning reparameterization from a module and the pruning method from the forward hook.</p>
 <p>The pruned parameter named <code class="docutils literal notranslate"><span class="pre">name</span></code> remains permanently pruned, and the parameter
 named <code class="docutils literal notranslate"><span class="pre">name+'_orig'</span></code> is removed from the parameter list. Similarly,
diff --git a/2.9/generated/torch.nn.utils.remove_spectral_norm.html b/2.9/generated/torch.nn.utils.remove_spectral_norm.html
index dd99a804f72..3f02b416e7c 100644
--- a/2.9/generated/torch.nn.utils.remove_spectral_norm.html
+++ b/2.9/generated/torch.nn.utils.remove_spectral_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.remove_spectral_norm<a class="headerlink" href="#torch-nn-utils-remove-spectral-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.remove_spectral_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">remove_spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/spectral_norm.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.remove_spectral_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">remove_spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/spectral_norm.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.remove_spectral_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the spectral normalization reparameterization from a module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.remove_weight_norm.html b/2.9/generated/torch.nn.utils.remove_weight_norm.html
index 5cdf70138ea..3d7a44c51dd 100644
--- a/2.9/generated/torch.nn.utils.remove_weight_norm.html
+++ b/2.9/generated/torch.nn.utils.remove_weight_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.remove_weight_norm<a class="headerlink" href="#torch-nn-utils-remove-weight-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.remove_weight_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">remove_weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/weight_norm.py#L148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.remove_weight_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">remove_weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/weight_norm.py#L148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.remove_weight_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the weight normalization reparameterization from a module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.rnn.PackedSequence.html b/2.9/generated/torch.nn.utils.rnn.PackedSequence.html
index f12f2e13f45..0f7a44e6f7b 100644
--- a/2.9/generated/torch.nn.utils.rnn.PackedSequence.html
+++ b/2.9/generated/torch.nn.utils.rnn.PackedSequence.html
@@ -4404,7 +4404,7 @@
 <h1>PackedSequence<a class="headerlink" href="#packedsequence" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.PackedSequence">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">PackedSequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sorted_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unsorted_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.PackedSequence" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">PackedSequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sorted_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unsorted_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.PackedSequence" title="Permalink to this definition">#</a></dt>
 <dd><p>Holds the data and list of <a class="reference internal" href="#torch.nn.utils.rnn.PackedSequence.batch_sizes" title="torch.nn.utils.rnn.PackedSequence.batch_sizes"><code class="xref py py-attr docutils literal notranslate"><span class="pre">batch_sizes</span></code></a> of a packed sequence.</p>
 <p>All RNN modules accept packed sequences as inputs.</p>
 <div class="admonition note">
@@ -4476,7 +4476,7 @@ <h1>PackedSequence<a class="headerlink" href="#packedsequence" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.PackedSequence.is_pinned">
-<span class="sig-name descname"><span class="pre">is_pinned</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.PackedSequence.is_pinned" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_pinned</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L206"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.PackedSequence.is_pinned" title="Permalink to this definition">#</a></dt>
 <dd><p>Return true if <cite>self.data</cite> stored on in pinned memory.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4493,7 +4493,7 @@ <h1>PackedSequence<a class="headerlink" href="#packedsequence" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.PackedSequence.to">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../tensor_attributes.html#torch.dtype" title="torch.dtype"><span class="pre">dtype</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">copy</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Self</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.PackedSequence.to" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../tensor_attributes.html#torch.dtype" title="torch.dtype"><span class="pre">dtype</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">copy</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Self</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.PackedSequence.to" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><span class="pre">Union</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensor_attributes.html#torch.device" title="torch.device"><span class="pre">device</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.14)"><span class="pre">Optional</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensor_attributes.html#torch.dtype" title="torch.dtype"><span class="pre">dtype</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">copy</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.14)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">...</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Self</span></span></span></dt>
 <dt class="sig sig-object py">
diff --git a/2.9/generated/torch.nn.utils.rnn.invert_permutation.html b/2.9/generated/torch.nn.utils.rnn.invert_permutation.html
index 90a61b937ca..a7b1fa07f05 100644
--- a/2.9/generated/torch.nn.utils.rnn.invert_permutation.html
+++ b/2.9/generated/torch.nn.utils.rnn.invert_permutation.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.rnn.invert_permutation<a class="headerlink" href="#torch-nn-utils-rnn-invert-permutation" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.invert_permutation">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">invert_permutation</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">permutation</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.invert_permutation" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">invert_permutation</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">permutation</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.invert_permutation" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the inverse of <code class="docutils literal notranslate"><span class="pre">permutation</span></code>.</p>
 <p>This is useful for converting between sorted and unsorted indices in
 a <code class="xref py py-class docutils literal notranslate"><span class="pre">PackedSequence</span></code>.</p>
diff --git a/2.9/generated/torch.nn.utils.rnn.pack_padded_sequence.html b/2.9/generated/torch.nn.utils.rnn.pack_padded_sequence.html
index 5ddd37cd72f..c846b804d70 100644
--- a/2.9/generated/torch.nn.utils.rnn.pack_padded_sequence.html
+++ b/2.9/generated/torch.nn.utils.rnn.pack_padded_sequence.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.rnn.pack_padded_sequence<a class="headerlink" href="#torch-nn-utils-rnn-pack-padded-sequence" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.pack_padded_sequence">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">pack_padded_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enforce_sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.pack_padded_sequence" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">pack_padded_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enforce_sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.pack_padded_sequence" title="Permalink to this definition">#</a></dt>
 <dd><p>Packs a Tensor containing padded sequences of variable length.</p>
 <p><code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> can be of size <code class="docutils literal notranslate"><span class="pre">T</span> <span class="pre">x</span> <span class="pre">B</span> <span class="pre">x</span> <span class="pre">*</span></code> (if <code class="xref py py-attr docutils literal notranslate"><span class="pre">batch_first</span></code> is <code class="docutils literal notranslate"><span class="pre">False</span></code>)
 or <code class="docutils literal notranslate"><span class="pre">B</span> <span class="pre">x</span> <span class="pre">T</span> <span class="pre">x</span> <span class="pre">*</span></code> (if <code class="xref py py-attr docutils literal notranslate"><span class="pre">batch_first</span></code> is <code class="docutils literal notranslate"><span class="pre">True</span></code>) where <code class="docutils literal notranslate"><span class="pre">T</span></code> is the length
diff --git a/2.9/generated/torch.nn.utils.rnn.pack_sequence.html b/2.9/generated/torch.nn.utils.rnn.pack_sequence.html
index fdfdf215040..01a26c48d9e 100644
--- a/2.9/generated/torch.nn.utils.rnn.pack_sequence.html
+++ b/2.9/generated/torch.nn.utils.rnn.pack_sequence.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.rnn.pack_sequence<a class="headerlink" href="#torch-nn-utils-rnn-pack-sequence" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.pack_sequence">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">pack_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequences</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enforce_sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L539"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.pack_sequence" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">pack_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequences</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enforce_sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L539"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.pack_sequence" title="Permalink to this definition">#</a></dt>
 <dd><p>Packs a list of variable length Tensors.</p>
 <p>Consecutive call of the next functions: <code class="docutils literal notranslate"><span class="pre">pad_sequence</span></code>, <code class="docutils literal notranslate"><span class="pre">pack_padded_sequence</span></code>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">sequences</span></code> should be a list of Tensors of size <code class="docutils literal notranslate"><span class="pre">L</span> <span class="pre">x</span> <span class="pre">*</span></code>, where <cite>L</cite> is
diff --git a/2.9/generated/torch.nn.utils.rnn.pad_packed_sequence.html b/2.9/generated/torch.nn.utils.rnn.pad_packed_sequence.html
index c9e0fe9d984..3aaaef713f0 100644
--- a/2.9/generated/torch.nn.utils.rnn.pad_packed_sequence.html
+++ b/2.9/generated/torch.nn.utils.rnn.pad_packed_sequence.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.rnn.pad_packed_sequence<a class="headerlink" href="#torch-nn-utils-rnn-pad-packed-sequence" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.pad_packed_sequence">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">pad_packed_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequence</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L344"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.pad_packed_sequence" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">pad_packed_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequence</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L344"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.pad_packed_sequence" title="Permalink to this definition">#</a></dt>
 <dd><p>Pad a packed batch of variable length sequences.</p>
 <p>It is an inverse operation to <a class="reference internal" href="torch.nn.utils.rnn.pack_padded_sequence.html#torch.nn.utils.rnn.pack_padded_sequence" title="torch.nn.utils.rnn.pack_padded_sequence"><code class="xref py py-func docutils literal notranslate"><span class="pre">pack_padded_sequence()</span></code></a>.</p>
 <p>The returned Tensor’s data will be of size <code class="docutils literal notranslate"><span class="pre">T</span> <span class="pre">x</span> <span class="pre">B</span> <span class="pre">x</span> <span class="pre">*</span></code> (if <code class="xref py py-attr docutils literal notranslate"><span class="pre">batch_first</span></code> is <code class="docutils literal notranslate"><span class="pre">False</span></code>)
diff --git a/2.9/generated/torch.nn.utils.rnn.pad_sequence.html b/2.9/generated/torch.nn.utils.rnn.pad_sequence.html
index d37f31c654c..0cc153ec033 100644
--- a/2.9/generated/torch.nn.utils.rnn.pad_sequence.html
+++ b/2.9/generated/torch.nn.utils.rnn.pad_sequence.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.rnn.pad_sequence<a class="headerlink" href="#torch-nn-utils-rnn-pad-sequence" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.pad_sequence">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">pad_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequences</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_side</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'right'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.pad_sequence" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">pad_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sequences</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">padding_side</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'right'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.pad_sequence" title="Permalink to this definition">#</a></dt>
 <dd><p>Pad a list of variable length Tensors with <code class="xref py py-attr docutils literal notranslate"><span class="pre">padding_value</span></code>.</p>
 <p><code class="docutils literal notranslate"><span class="pre">pad_sequence</span></code> stacks a list of Tensors along a new dimension, and pads them
 to equal length. <code class="xref py py-attr docutils literal notranslate"><span class="pre">sequences</span></code> can be list of sequences with size <code class="docutils literal notranslate"><span class="pre">L</span> <span class="pre">x</span> <span class="pre">*</span></code>,
diff --git a/2.9/generated/torch.nn.utils.rnn.unpack_sequence.html b/2.9/generated/torch.nn.utils.rnn.unpack_sequence.html
index 626d3c2c50f..e3efa21d0af 100644
--- a/2.9/generated/torch.nn.utils.rnn.unpack_sequence.html
+++ b/2.9/generated/torch.nn.utils.rnn.unpack_sequence.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.rnn.unpack_sequence<a class="headerlink" href="#torch-nn-utils-rnn-unpack-sequence" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.unpack_sequence">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">unpack_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">packed_sequences</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.unpack_sequence" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">unpack_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">packed_sequences</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L578"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.unpack_sequence" title="Permalink to this definition">#</a></dt>
 <dd><p>Unpack PackedSequence into a list of variable length Tensors.</p>
 <p><code class="docutils literal notranslate"><span class="pre">packed_sequences</span></code> should be a PackedSequence object.</p>
 <p class="rubric">Example</p>
diff --git a/2.9/generated/torch.nn.utils.rnn.unpad_sequence.html b/2.9/generated/torch.nn.utils.rnn.unpad_sequence.html
index 44e75703644..cde3cb68e69 100644
--- a/2.9/generated/torch.nn.utils.rnn.unpad_sequence.html
+++ b/2.9/generated/torch.nn.utils.rnn.unpad_sequence.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.rnn.unpad_sequence<a class="headerlink" href="#torch-nn-utils-rnn-unpad-sequence" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.rnn.unpad_sequence">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">unpad_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padded_sequences</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/rnn.py#L490"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.unpad_sequence" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.rnn.</span></span><span class="sig-name descname"><span class="pre">unpad_sequence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">padded_sequences</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">batch_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/rnn.py#L490"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.rnn.unpad_sequence" title="Permalink to this definition">#</a></dt>
 <dd><p>Unpad padded Tensor into a list of variable length Tensors.</p>
 <p><code class="docutils literal notranslate"><span class="pre">unpad_sequence</span></code> unstacks padded Tensor into a list of variable length Tensors.</p>
 <p class="rubric">Example</p>
diff --git a/2.9/generated/torch.nn.utils.skip_init.html b/2.9/generated/torch.nn.utils.skip_init.html
index d612f975b22..b13258dc9be 100644
--- a/2.9/generated/torch.nn.utils.skip_init.html
+++ b/2.9/generated/torch.nn.utils.skip_init.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.skip_init<a class="headerlink" href="#torch-nn-utils-skip-init" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.skip_init">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">skip_init</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_cls</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/init.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.skip_init" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">skip_init</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_cls</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/init.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.skip_init" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a module class object and args / kwargs, instantiate the module without initializing parameters / buffers.</p>
 <p>This can be useful if initialization is slow or if custom initialization will
 be performed, making the default initialization unnecessary. There are some caveats to this, due to
diff --git a/2.9/generated/torch.nn.utils.spectral_norm.html b/2.9/generated/torch.nn.utils.spectral_norm.html
index 721b613ee6f..5a8adabcfba 100644
--- a/2.9/generated/torch.nn.utils.spectral_norm.html
+++ b/2.9/generated/torch.nn.utils.spectral_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.spectral_norm<a class="headerlink" href="#torch-nn-utils-spectral-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.spectral_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_power_iterations</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/spectral_norm.py#L266"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.spectral_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_power_iterations</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/spectral_norm.py#L266"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.spectral_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply spectral normalization to a parameter in the given module.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><msub><mi mathvariant="bold">W</mi><mrow><mi>S</mi><mi>N</mi></mrow></msub><mo>=</mo><mfrac><mi mathvariant="bold">W</mi><mrow><mi>σ</mi><mo stretchy="false">(</mo><mi mathvariant="bold">W</mi><mo stretchy="false">)</mo></mrow></mfrac><mo separator="true">,</mo><mi>σ</mi><mo stretchy="false">(</mo><mi mathvariant="bold">W</mi><mo stretchy="false">)</mo><mo>=</mo><munder><mrow><mi>max</mi><mo>⁡</mo></mrow><mrow><mi mathvariant="bold">h</mi><mo>:</mo><mi mathvariant="bold">h</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></munder><mfrac><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">W</mi><mi mathvariant="bold">h</mi><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub></mrow><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">h</mi><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub></mrow></mfrac></mrow><annotation encoding="application/x-tex">\mathbf{W}_{SN} = \dfrac{\mathbf{W}}{\sigma(\mathbf{W})},
diff --git a/2.9/generated/torch.nn.utils.spectral_norm.remove_spectral_norm.html b/2.9/generated/torch.nn.utils.spectral_norm.remove_spectral_norm.html
index 28387b940f4..5ce5ab91a73 100644
--- a/2.9/generated/torch.nn.utils.spectral_norm.remove_spectral_norm.html
+++ b/2.9/generated/torch.nn.utils.spectral_norm.remove_spectral_norm.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.spectral_norm.remove_spectral_norm<a class="headerlink" href="#torch-nn-utils-spectral-norm-remove-spectral-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.spectral_norm.remove_spectral_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.spectral_norm.</span></span><span class="sig-name descname"><span class="pre">remove_spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/spectral_norm.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.spectral_norm.remove_spectral_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.spectral_norm.</span></span><span class="sig-name descname"><span class="pre">remove_spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/spectral_norm.py#L338"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.spectral_norm.remove_spectral_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the spectral normalization reparameterization from a module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.spectral_norm.spectral_norm.html b/2.9/generated/torch.nn.utils.spectral_norm.spectral_norm.html
index 47ca01ca70b..0fe42c4a251 100644
--- a/2.9/generated/torch.nn.utils.spectral_norm.spectral_norm.html
+++ b/2.9/generated/torch.nn.utils.spectral_norm.spectral_norm.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.spectral_norm.spectral_norm<a class="headerlink" href="#torch-nn-utils-spectral-norm-spectral-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.spectral_norm.spectral_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.spectral_norm.</span></span><span class="sig-name descname"><span class="pre">spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_power_iterations</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/spectral_norm.py#L266"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.spectral_norm.spectral_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.spectral_norm.</span></span><span class="sig-name descname"><span class="pre">spectral_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_power_iterations</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/spectral_norm.py#L266"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.spectral_norm.spectral_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply spectral normalization to a parameter in the given module.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><msub><mi mathvariant="bold">W</mi><mrow><mi>S</mi><mi>N</mi></mrow></msub><mo>=</mo><mfrac><mi mathvariant="bold">W</mi><mrow><mi>σ</mi><mo stretchy="false">(</mo><mi mathvariant="bold">W</mi><mo stretchy="false">)</mo></mrow></mfrac><mo separator="true">,</mo><mi>σ</mi><mo stretchy="false">(</mo><mi mathvariant="bold">W</mi><mo stretchy="false">)</mo><mo>=</mo><munder><mrow><mi>max</mi><mo>⁡</mo></mrow><mrow><mi mathvariant="bold">h</mi><mo>:</mo><mi mathvariant="bold">h</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></munder><mfrac><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">W</mi><mi mathvariant="bold">h</mi><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub></mrow><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">h</mi><msub><mi mathvariant="normal">∥</mi><mn>2</mn></msub></mrow></mfrac></mrow><annotation encoding="application/x-tex">\mathbf{W}_{SN} = \dfrac{\mathbf{W}}{\sigma(\mathbf{W})},
diff --git a/2.9/generated/torch.nn.utils.stateless.functional_call.html b/2.9/generated/torch.nn.utils.stateless.functional_call.html
index c31bcc28440..f32d7f64f3d 100644
--- a/2.9/generated/torch.nn.utils.stateless.functional_call.html
+++ b/2.9/generated/torch.nn.utils.stateless.functional_call.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.stateless.functional_call<a class="headerlink" href="#torch-nn-utils-stateless-functional-call" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.stateless.functional_call">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.stateless.</span></span><span class="sig-name descname"><span class="pre">functional_call</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameters_and_buffers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/stateless.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.stateless.functional_call" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.stateless.</span></span><span class="sig-name descname"><span class="pre">functional_call</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameters_and_buffers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tie_weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/stateless.py#L162"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.stateless.functional_call" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a functional call on the module by replacing the module parameters and buffers with the provided ones.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.nn.utils.vector_to_parameters.html b/2.9/generated/torch.nn.utils.vector_to_parameters.html
index 3c5147a442d..0d36ba49d7d 100644
--- a/2.9/generated/torch.nn.utils.vector_to_parameters.html
+++ b/2.9/generated/torch.nn.utils.vector_to_parameters.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.vector_to_parameters<a class="headerlink" href="#torch-nn-utils-vector-to-parameters" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.vector_to_parameters">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">vector_to_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/convert_parameters.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.vector_to_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">vector_to_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vec</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/convert_parameters.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.vector_to_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy slices of a vector into an iterable of parameters.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.weight_norm.html b/2.9/generated/torch.nn.utils.weight_norm.html
index ffd2ba522f1..ab7a78f8c09 100644
--- a/2.9/generated/torch.nn.utils.weight_norm.html
+++ b/2.9/generated/torch.nn.utils.weight_norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.nn.utils.weight_norm<a class="headerlink" href="#torch-nn-utils-weight-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.weight_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/weight_norm.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.weight_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.</span></span><span class="sig-name descname"><span class="pre">weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/weight_norm.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.weight_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply weight normalization to a parameter in the given module.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mi mathvariant="bold">w</mi><mo>=</mo><mi>g</mi><mfrac><mi mathvariant="bold">v</mi><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">v</mi><mi mathvariant="normal">∥</mi></mrow></mfrac></mrow><annotation encoding="application/x-tex">\mathbf{w} = g \dfrac{\mathbf{v}}{\|\mathbf{v}\|}
diff --git a/2.9/generated/torch.nn.utils.weight_norm.remove_weight_norm.html b/2.9/generated/torch.nn.utils.weight_norm.remove_weight_norm.html
index 0b235b7af1e..34f4cc02264 100644
--- a/2.9/generated/torch.nn.utils.weight_norm.remove_weight_norm.html
+++ b/2.9/generated/torch.nn.utils.weight_norm.remove_weight_norm.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.weight_norm.remove_weight_norm<a class="headerlink" href="#torch-nn-utils-weight-norm-remove-weight-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.weight_norm.remove_weight_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.weight_norm.</span></span><span class="sig-name descname"><span class="pre">remove_weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/weight_norm.py#L148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.weight_norm.remove_weight_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.weight_norm.</span></span><span class="sig-name descname"><span class="pre">remove_weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/weight_norm.py#L148"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.weight_norm.remove_weight_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Remove the weight normalization reparameterization from a module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.nn.utils.weight_norm.weight_norm.html b/2.9/generated/torch.nn.utils.weight_norm.weight_norm.html
index 5b5fa98bb44..1a66edc062a 100644
--- a/2.9/generated/torch.nn.utils.weight_norm.weight_norm.html
+++ b/2.9/generated/torch.nn.utils.weight_norm.weight_norm.html
@@ -4415,7 +4415,7 @@
 <h1>torch.nn.utils.weight_norm.weight_norm<a class="headerlink" href="#torch-nn-utils-weight-norm-weight-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.utils.weight_norm.weight_norm">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.weight_norm.</span></span><span class="sig-name descname"><span class="pre">weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/utils/weight_norm.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.weight_norm.weight_norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.utils.weight_norm.</span></span><span class="sig-name descname"><span class="pre">weight_norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'weight'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/utils/weight_norm.py#L84"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.utils.weight_norm.weight_norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply weight normalization to a parameter in the given module.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><mi mathvariant="bold">w</mi><mo>=</mo><mi>g</mi><mfrac><mi mathvariant="bold">v</mi><mrow><mi mathvariant="normal">∥</mi><mi mathvariant="bold">v</mi><mi mathvariant="normal">∥</mi></mrow></mfrac></mrow><annotation encoding="application/x-tex">\mathbf{w} = g \dfrac{\mathbf{v}}{\|\mathbf{v}\|}
diff --git a/2.9/generated/torch.no_grad.html b/2.9/generated/torch.no_grad.html
index 2c9f77aef1e..3f70b7d8ec0 100644
--- a/2.9/generated/torch.no_grad.html
+++ b/2.9/generated/torch.no_grad.html
@@ -4404,7 +4404,7 @@
 <h1>no_grad<a class="headerlink" href="#no-grad" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.no_grad">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">no_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">orig_func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/autograd/grad_mode.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.no_grad" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">no_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">orig_func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/autograd/grad_mode.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.no_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that disables gradient calculation.</p>
 <p>Disabling gradient calculation is useful for inference, when you are sure
 that you will not call <a class="reference internal" href="torch.Tensor.backward.html#torch.Tensor.backward" title="torch.Tensor.backward"><code class="xref py py-meth docutils literal notranslate"><span class="pre">Tensor.backward()</span></code></a>. It will reduce memory
diff --git a/2.9/generated/torch.norm.html b/2.9/generated/torch.norm.html
index c670f11f814..f8496d7fdc5 100644
--- a/2.9/generated/torch.norm.html
+++ b/2.9/generated/torch.norm.html
@@ -4404,7 +4404,7 @@
 <h1>torch.norm<a class="headerlink" href="#torch-norm" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.norm">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fro'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.norm" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">norm</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fro'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keepdim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1660"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.norm" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the matrix norm or vector norm of a given tensor.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.optim.ASGD.html b/2.9/generated/torch.optim.ASGD.html
index 236142206a7..e26a9acb26a 100644
--- a/2.9/generated/torch.optim.ASGD.html
+++ b/2.9/generated/torch.optim.ASGD.html
@@ -4404,7 +4404,7 @@
 <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.ASGD">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">ASGD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t0</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000000.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/asgd.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">ASGD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t0</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000000.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/asgd.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Averaged Stochastic Gradient Descent.</p>
 <p>It has been proposed in <a class="reference external" href="https://meyn.ece.ufl.edu/wp-content/uploads/sites/77/archive/spm_files/Courses/ECE555-2011/555media/poljud92.pdf">Acceleration of stochastic approximation by
 averaging</a>.</p>
@@ -4443,7 +4443,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4457,7 +4457,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4510,7 +4510,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4544,7 +4544,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4581,7 +4581,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4613,7 +4613,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4645,7 +4645,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4668,7 +4668,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4693,7 +4693,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4756,7 +4756,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/asgd.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/asgd.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4768,7 +4768,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.ASGD.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.ASGD.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Adadelta.html b/2.9/generated/torch.optim.Adadelta.html
index 98629e8e7ce..1efc2eee4be 100644
--- a/2.9/generated/torch.optim.Adadelta.html
+++ b/2.9/generated/torch.optim.Adadelta.html
@@ -4404,7 +4404,7 @@
 <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.Adadelta">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Adadelta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rho</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.9</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adadelta.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Adadelta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rho</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.9</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adadelta.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Adadelta algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>ρ</mi><mtext> (decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> </mtext><mtext> (square avg)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>u</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> </mtext><mtext> (accumulate variables)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mi>ρ</mi><mo>+</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>ρ</mi><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi mathvariant="normal">Δ</mi><msub><mi>x</mi><mi>t</mi></msub><mo>←</mo><mfrac><msqrt><mrow><msub><mi>u</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mi>ϵ</mi></mrow></msqrt><msqrt><mrow><msub><mi>v</mi><mi>t</mi></msub><mo>+</mo><mi>ϵ</mi></mrow></msqrt></mfrac><msub><mi>g</mi><mi>t</mi></msub><mspace width="5.9751em"/></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>u</mi><mi>t</mi></msub><mo>←</mo><msub><mi>u</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mi>ρ</mi><mo>+</mo><mi mathvariant="normal">Δ</mi><msubsup><mi>x</mi><mi>t</mi><mn>2</mn></msubsup><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>ρ</mi><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><mi mathvariant="normal">Δ</mi><msub><mi>x</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4492,7 +4492,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4506,7 +4506,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4559,7 +4559,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4593,7 +4593,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4630,7 +4630,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4662,7 +4662,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4694,7 +4694,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4717,7 +4717,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4742,7 +4742,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4805,7 +4805,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adadelta.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adadelta.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4817,7 +4817,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adadelta.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adadelta.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Adafactor.html b/2.9/generated/torch.optim.Adafactor.html
index a31b6366185..5bcb3f656b8 100644
--- a/2.9/generated/torch.optim.Adafactor.html
+++ b/2.9/generated/torch.optim.Adafactor.html
@@ -4634,7 +4634,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4648,7 +4648,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4701,7 +4701,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4735,7 +4735,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4772,7 +4772,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4804,7 +4804,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4836,7 +4836,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4859,7 +4859,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4884,7 +4884,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4947,7 +4947,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/_adafactor.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/_adafactor.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4959,7 +4959,7 @@ <h1>Adafactor<a class="headerlink" href="#adafactor" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adafactor.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adafactor.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Adagrad.html b/2.9/generated/torch.optim.Adagrad.html
index 89475d24d16..ec50b73da99 100644
--- a/2.9/generated/torch.optim.Adagrad.html
+++ b/2.9/generated/torch.optim.Adagrad.html
@@ -4404,7 +4404,7 @@
 <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.Adagrad">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Adagrad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">initial_accumulator_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adagrad.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Adagrad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">initial_accumulator_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adagrad.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Adagrad algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><mi>τ</mi><mtext> (initial accumulator value)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>η</mi><mtext> (lr decay)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><mi>s</mi><mi>t</mi><mi>a</mi><mi>t</mi><mi>e</mi><mi mathvariant="normal">_</mi><mi>s</mi><mi>u</mi><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mi>τ</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><mi>γ</mi><mo>~</mo></mover><mo>←</mo><mi>γ</mi><mi mathvariant="normal">/</mi><mo stretchy="false">(</mo><mn>1</mn><mo>+</mo><mo stretchy="false">(</mo><mi>t</mi><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mi>η</mi><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>s</mi><mi>t</mi><mi>a</mi><mi>t</mi><mi>e</mi><mi mathvariant="normal">_</mi><mi>s</mi><mi>u</mi><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><mi>s</mi><mi>t</mi><mi>a</mi><mi>t</mi><mi>e</mi><mi mathvariant="normal">_</mi><mi>s</mi><mi>u</mi><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mover accent="true"><mi>γ</mi><mo>~</mo></mover><mfrac><msub><mi>g</mi><mi>t</mi></msub><mrow><msqrt><mrow><mi>s</mi><mi>t</mi><mi>a</mi><mi>t</mi><mi>e</mi><mi mathvariant="normal">_</mi><mi>s</mi><mi>u</mi><msub><mi>m</mi><mi>t</mi></msub></mrow></msqrt><mo>+</mo><mi>ϵ</mi></mrow></mfrac></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4475,7 +4475,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4489,7 +4489,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4542,7 +4542,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4576,7 +4576,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4613,7 +4613,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4645,7 +4645,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4677,7 +4677,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4700,7 +4700,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4725,13 +4725,13 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.share_memory">
-<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adagrad.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.share_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adagrad.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.share_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>Calls tensor.share_memory_() on the state sum tensors.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4794,7 +4794,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adagrad.py#L147"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adagrad.py#L147"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4806,7 +4806,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adagrad.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adagrad.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Adam.html b/2.9/generated/torch.optim.Adam.html
index def4b55f086..8e772de0e95 100644
--- a/2.9/generated/torch.optim.Adam.html
+++ b/2.9/generated/torch.optim.Adam.html
@@ -4404,7 +4404,7 @@
 <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.Adam">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Adam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adam.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Adam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adam.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Adam algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext> (betas)</mtext><mo separator="true">,</mo><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">amsgrad</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo separator="true">,</mo><mtext> </mtext><mi>ϵ</mi><mtext> (epsilon)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( first moment)</mtext><mo separator="true">,</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> (second moment)</mtext><mo separator="true">,</mo><mtext> </mtext><msubsup><mi>v</mi><mn>0</mn><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo>←</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>m</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>1</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>a</mi><mi>m</mi><mi>s</mi><mi>g</mi><mi>r</mi><mi>a</mi><mi>d</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msubsup><mi>v</mi><mi>t</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">a</mi><mi mathvariant="normal">x</mi></mrow><mo stretchy="false">(</mo><msubsup><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo separator="true">,</mo><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msubsup><mi>v</mi><mi>t</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>v</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4515,7 +4515,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4529,7 +4529,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4582,7 +4582,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4616,7 +4616,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4653,7 +4653,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4685,7 +4685,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4717,7 +4717,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4740,7 +4740,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4765,7 +4765,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4828,7 +4828,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adam.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adam.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4840,7 +4840,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adam.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adam.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.AdamW.html b/2.9/generated/torch.optim.AdamW.html
index c52b80698b8..025cacf7a5d 100644
--- a/2.9/generated/torch.optim.AdamW.html
+++ b/2.9/generated/torch.optim.AdamW.html
@@ -4404,7 +4404,7 @@
 <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.AdamW">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">AdamW</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adamw.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">AdamW</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adamw.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements AdamW algorithm, where weight decay does not accumulate in the momentum nor variance.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext>(lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext>(betas)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext>(params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext>(objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>ϵ</mi><mtext> (epsilon)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>λ</mi><mtext>(weight decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">amsgrad</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">maximize</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> (first moment)</mtext><mo separator="true">,</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( second moment)</mtext><mo separator="true">,</mo><mtext> </mtext><msubsup><mi>v</mi><mn>0</mn><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo>←</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>m</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>1</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>a</mi><mi>m</mi><mi>s</mi><mi>g</mi><mi>r</mi><mi>a</mi><mi>d</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msubsup><mi>v</mi><mi>t</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">a</mi><mi mathvariant="normal">x</mi></mrow><mo stretchy="false">(</mo><msubsup><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo separator="true">,</mo><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msubsup><mi>v</mi><mi>t</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>v</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4512,7 +4512,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4526,7 +4526,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4579,7 +4579,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4613,7 +4613,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4650,7 +4650,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4682,7 +4682,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4714,7 +4714,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4737,7 +4737,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4762,7 +4762,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4825,7 +4825,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adam.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adam.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4837,7 +4837,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.AdamW.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.AdamW.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Adamax.html b/2.9/generated/torch.optim.Adamax.html
index f7f8395e43e..c666244ef04 100644
--- a/2.9/generated/torch.optim.Adamax.html
+++ b/2.9/generated/torch.optim.Adamax.html
@@ -4404,7 +4404,7 @@
 <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.Adamax">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Adamax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.002</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adamax.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Adamax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.002</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adamax.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Adamax algorithm (a variant of Adam based on infinity norm).</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext> (betas)</mtext><mo separator="true">,</mo><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>ϵ</mi><mtext> (epsilon)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( first moment)</mtext><mo separator="true">,</mo><msub><mi>u</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( infinity norm)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>u</mi><mi>t</mi></msub><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">a</mi><mi mathvariant="normal">x</mi></mrow><mo stretchy="false">(</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>u</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo separator="true">,</mo><mi mathvariant="normal">∣</mi><msub><mi>g</mi><mi>t</mi></msub><mi mathvariant="normal">∣</mi><mo>+</mo><mi>ϵ</mi><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mfrac><mrow><mi>γ</mi><msub><mi>m</mi><mi>t</mi></msub></mrow><mrow><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>1</mn><mi>t</mi></msubsup><mo stretchy="false">)</mo><msub><mi>u</mi><mi>t</mi></msub></mrow></mfrac></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4465,7 +4465,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4479,7 +4479,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4532,7 +4532,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4566,7 +4566,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4603,7 +4603,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4635,7 +4635,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4667,7 +4667,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4690,7 +4690,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4715,7 +4715,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4778,7 +4778,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adamax.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adamax.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4790,7 +4790,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Adamax.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Adamax.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.LBFGS.html b/2.9/generated/torch.optim.LBFGS.html
index 25569566e45..ac5f8733070 100644
--- a/2.9/generated/torch.optim.LBFGS.html
+++ b/2.9/generated/torch.optim.LBFGS.html
@@ -4404,7 +4404,7 @@
 <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.LBFGS">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">LBFGS</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_eval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tolerance_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tolerance_change</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-09</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">history_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">line_search_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lbfgs.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">LBFGS</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_eval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tolerance_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tolerance_change</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-09</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">history_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">line_search_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lbfgs.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements L-BFGS algorithm.</p>
 <p>Heavily inspired by <a class="reference external" href="https://www.cs.ubc.ca/~schmidtm/Software/minFunc.html">minFunc</a>.</p>
 <div class="admonition warning">
@@ -4443,7 +4443,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4457,7 +4457,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4510,7 +4510,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4544,7 +4544,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4581,7 +4581,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4613,7 +4613,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4645,7 +4645,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4668,7 +4668,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4693,7 +4693,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4756,7 +4756,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lbfgs.py#L301"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lbfgs.py#L301"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4768,7 +4768,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.LBFGS.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.LBFGS.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Muon.html b/2.9/generated/torch.optim.Muon.html
index 7dbe61f2bf8..18d6273aee2 100644
--- a/2.9/generated/torch.optim.Muon.html
+++ b/2.9/generated/torch.optim.Muon.html
@@ -4500,7 +4500,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4514,7 +4514,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4567,7 +4567,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4601,7 +4601,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4638,7 +4638,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4670,7 +4670,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4702,7 +4702,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4725,7 +4725,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4750,7 +4750,7 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4813,13 +4813,13 @@ <h1>Muon<a class="headerlink" href="#muon" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/_muon.py#L166"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/_muon.py#L166"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs a single optimization step.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Muon.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Muon.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.NAdam.html b/2.9/generated/torch.optim.NAdam.html
index c82d59acae7..13571d004bd 100644
--- a/2.9/generated/torch.optim.NAdam.html
+++ b/2.9/generated/torch.optim.NAdam.html
@@ -4404,7 +4404,7 @@
 <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.NAdam">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">NAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.002</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.004</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/nadam.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">NAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.002</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.004</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/nadam.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements NAdam algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><msub><mi>γ</mi><mi>t</mi></msub><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext> (betas)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>ψ</mi><mtext> (momentum decay)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mtext> </mtext><mtext mathvariant="italic">decoupled_weight_decay</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">maximize</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( first moment)</mtext><mo separator="true">,</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( second moment)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">decoupled_weight_decay</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>μ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><mfrac><mn>1</mn><mn>2</mn></mfrac><msup><mn>0.96</mn><mrow><mi>t</mi><mi>ψ</mi></mrow></msup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>μ</mi><mrow><mi>t</mi><mo>+</mo><mn>1</mn></mrow></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><mfrac><mn>1</mn><mn>2</mn></mfrac><msup><mn>0.96</mn><mrow><mo stretchy="false">(</mo><mi>t</mi><mo>+</mo><mn>1</mn><mo stretchy="false">)</mo><mi>ψ</mi></mrow></msup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>μ</mi><mrow><mi>t</mi><mo>+</mo><mn>1</mn></mrow></msub><msub><mi>m</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><munderover><mo>∏</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mrow><mi>t</mi><mo>+</mo><mn>1</mn></mrow></munderover><msub><mi>μ</mi><mi>i</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.1298em"/><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>μ</mi><mi>t</mi></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><munderover><mo>∏</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mi>t</mi></munderover><msub><mi>μ</mi><mi>i</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>v</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4496,7 +4496,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4510,7 +4510,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4563,7 +4563,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4597,7 +4597,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4634,7 +4634,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4666,7 +4666,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4698,7 +4698,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4721,7 +4721,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4746,7 +4746,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4809,7 +4809,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/nadam.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/nadam.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4821,7 +4821,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.NAdam.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.NAdam.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Optimizer.add_param_group.html b/2.9/generated/torch.optim.Optimizer.add_param_group.html
index b4247cf3dbe..db22ca45b3f 100644
--- a/2.9/generated/torch.optim.Optimizer.add_param_group.html
+++ b/2.9/generated/torch.optim.Optimizer.add_param_group.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.add_param_group<a class="headerlink" href="#torch-optim-optimizer-add-param-group" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.add_param_group">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
diff --git a/2.9/generated/torch.optim.Optimizer.load_state_dict.html b/2.9/generated/torch.optim.Optimizer.load_state_dict.html
index 8ff7118df55..8c24d9fae0e 100644
--- a/2.9/generated/torch.optim.Optimizer.load_state_dict.html
+++ b/2.9/generated/torch.optim.Optimizer.load_state_dict.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.load_state_dict<a class="headerlink" href="#torch-optim-optimizer-load-state-dict" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.load_state_dict">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Optimizer.register_load_state_dict_post_hook.html b/2.9/generated/torch.optim.Optimizer.register_load_state_dict_post_hook.html
index 482bee0591d..6ded46c62ee 100644
--- a/2.9/generated/torch.optim.Optimizer.register_load_state_dict_post_hook.html
+++ b/2.9/generated/torch.optim.Optimizer.register_load_state_dict_post_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.register_load_state_dict_post_hook<a class="headerlink" href="#torch-optim-optimizer-register-load-state-dict-post-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.register_load_state_dict_post_hook">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
diff --git a/2.9/generated/torch.optim.Optimizer.register_load_state_dict_pre_hook.html b/2.9/generated/torch.optim.Optimizer.register_load_state_dict_pre_hook.html
index 4d43bf4fff5..f3f15e32a03 100644
--- a/2.9/generated/torch.optim.Optimizer.register_load_state_dict_pre_hook.html
+++ b/2.9/generated/torch.optim.Optimizer.register_load_state_dict_pre_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.register_load_state_dict_pre_hook<a class="headerlink" href="#torch-optim-optimizer-register-load-state-dict-pre-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.register_load_state_dict_pre_hook">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
diff --git a/2.9/generated/torch.optim.Optimizer.register_state_dict_post_hook.html b/2.9/generated/torch.optim.Optimizer.register_state_dict_post_hook.html
index 7e24c296146..88ea73dacc8 100644
--- a/2.9/generated/torch.optim.Optimizer.register_state_dict_post_hook.html
+++ b/2.9/generated/torch.optim.Optimizer.register_state_dict_post_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.register_state_dict_post_hook<a class="headerlink" href="#torch-optim-optimizer-register-state-dict-post-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.register_state_dict_post_hook">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
diff --git a/2.9/generated/torch.optim.Optimizer.register_state_dict_pre_hook.html b/2.9/generated/torch.optim.Optimizer.register_state_dict_pre_hook.html
index c5149699a5e..1d294cd356d 100644
--- a/2.9/generated/torch.optim.Optimizer.register_state_dict_pre_hook.html
+++ b/2.9/generated/torch.optim.Optimizer.register_state_dict_pre_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.register_state_dict_pre_hook<a class="headerlink" href="#torch-optim-optimizer-register-state-dict-pre-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.register_state_dict_pre_hook">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
diff --git a/2.9/generated/torch.optim.Optimizer.register_step_post_hook.html b/2.9/generated/torch.optim.Optimizer.register_step_post_hook.html
index 4a74fd08caf..002310257be 100644
--- a/2.9/generated/torch.optim.Optimizer.register_step_post_hook.html
+++ b/2.9/generated/torch.optim.Optimizer.register_step_post_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.register_step_post_hook<a class="headerlink" href="#torch-optim-optimizer-register-step-post-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.register_step_post_hook">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
diff --git a/2.9/generated/torch.optim.Optimizer.register_step_pre_hook.html b/2.9/generated/torch.optim.Optimizer.register_step_pre_hook.html
index 286727ddffa..55ff334aab0 100644
--- a/2.9/generated/torch.optim.Optimizer.register_step_pre_hook.html
+++ b/2.9/generated/torch.optim.Optimizer.register_step_pre_hook.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.register_step_pre_hook<a class="headerlink" href="#torch-optim-optimizer-register-step-pre-hook" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.register_step_pre_hook">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
diff --git a/2.9/generated/torch.optim.Optimizer.state_dict.html b/2.9/generated/torch.optim.Optimizer.state_dict.html
index 9d224d7e4a6..853b4d72731 100644
--- a/2.9/generated/torch.optim.Optimizer.state_dict.html
+++ b/2.9/generated/torch.optim.Optimizer.state_dict.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.state_dict<a class="headerlink" href="#torch-optim-optimizer-state-dict" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.state_dict">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
diff --git a/2.9/generated/torch.optim.Optimizer.step.html b/2.9/generated/torch.optim.Optimizer.step.html
index 722de44ce8f..adad6a6b73b 100644
--- a/2.9/generated/torch.optim.Optimizer.step.html
+++ b/2.9/generated/torch.optim.Optimizer.step.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.step<a class="headerlink" href="#torch-optim-optimizer-step" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.step">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><span class="pre">None</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1060"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><span class="pre">None</span></a></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1060"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.step" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Callable" title="(in Python v3.14)"><span class="pre">Callable</span></a><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><span class="pre">float</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.14)"><span class="pre">float</span></a></span></span></dt>
 <dd><p>Perform a single optimization step to update parameter.</p>
diff --git a/2.9/generated/torch.optim.Optimizer.zero_grad.html b/2.9/generated/torch.optim.Optimizer.zero_grad.html
index a790d31318a..5b85afb3c5f 100644
--- a/2.9/generated/torch.optim.Optimizer.zero_grad.html
+++ b/2.9/generated/torch.optim.Optimizer.zero_grad.html
@@ -4404,7 +4404,7 @@
 <h1>torch.optim.Optimizer.zero_grad<a class="headerlink" href="#torch-optim-optimizer-zero-grad" title="Permalink to this heading">#</a></h1>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Optimizer.zero_grad">
-<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">Optimizer.</span></span><span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.RAdam.html b/2.9/generated/torch.optim.RAdam.html
index fb3c5c8161e..634bce5c123 100644
--- a/2.9/generated/torch.optim.RAdam.html
+++ b/2.9/generated/torch.optim.RAdam.html
@@ -4404,7 +4404,7 @@
 <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.RAdam">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">RAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/radam.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">RAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/radam.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements RAdam algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext> (betas)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weightdecay)</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">maximize</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>ϵ</mi><mtext> (epsilon)</mtext><mo separator="true">,</mo><mtext mathvariant="italic">decoupled_weight_decay</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( first moment)</mtext><mo separator="true">,</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( second moment)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="5.1215em"/><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub><mo>←</mo><mn>2</mn><mi mathvariant="normal">/</mi><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">decoupled_weight_decay</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="5.1215em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mi>λ</mi><msub><mi>θ</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="5.1215em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>m</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>1</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><msub><mi>ρ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub><mo>−</mo><mn>2</mn><mi>t</mi><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><msub><mi>ρ</mi><mi>t</mi></msub><mo>&gt;</mo><mn>5</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>l</mi><mi>t</mi></msub><mo>←</mo><mfrac><msqrt><mrow><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo stretchy="false">)</mo></mrow></msqrt><mrow><msqrt><msub><mi>v</mi><mi>t</mi></msub></msqrt><mo>+</mo><mi>ϵ</mi></mrow></mfrac></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>r</mi><mi>t</mi></msub><mo>←</mo><msqrt><mfrac><mrow><mo stretchy="false">(</mo><msub><mi>ρ</mi><mi>t</mi></msub><mo>−</mo><mn>4</mn><mo stretchy="false">)</mo><mo stretchy="false">(</mo><msub><mi>ρ</mi><mi>t</mi></msub><mo>−</mo><mn>2</mn><mo stretchy="false">)</mo><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub></mrow><mrow><mo stretchy="false">(</mo><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub><mo>−</mo><mn>4</mn><mo stretchy="false">)</mo><mo stretchy="false">(</mo><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub><mo>−</mo><mn>2</mn><mo stretchy="false">)</mo><msub><mi>ρ</mi><mi>t</mi></msub></mrow></mfrac></msqrt></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><msub><mi>r</mi><mi>t</mi></msub><msub><mi>l</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4522,7 +4522,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4536,7 +4536,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4589,7 +4589,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4623,7 +4623,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4660,7 +4660,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4692,7 +4692,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4724,7 +4724,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4747,7 +4747,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4772,7 +4772,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4835,7 +4835,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/radam.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/radam.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4847,7 +4847,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RAdam.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RAdam.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.RMSprop.html b/2.9/generated/torch.optim.RMSprop.html
index c070096d784..9a32adfda8b 100644
--- a/2.9/generated/torch.optim.RMSprop.html
+++ b/2.9/generated/torch.optim.RMSprop.html
@@ -4404,7 +4404,7 @@
 <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.RMSprop">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">RMSprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.99</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">centered</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rmsprop.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">RMSprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.99</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">centered</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rmsprop.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements RMSprop algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>α</mi><mtext> (alpha)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>μ</mi><mtext> (momentum)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>c</mi><mi>e</mi><mi>n</mi><mi>t</mi><mi>e</mi><mi>r</mi><mi>e</mi><mi>d</mi><mo separator="true">,</mo><mtext> </mtext><mi>ϵ</mi><mtext> (epsilon)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> (square average)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mtext mathvariant="bold">b</mtext><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> (buffer)</mtext><mo separator="true">,</mo><mtext> </mtext><msubsup><mi>g</mi><mn>0</mn><mrow><mi>a</mi><mi>v</mi><mi>e</mi></mrow></msubsup><mo>←</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><mi>α</mi><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>α</mi><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup><mspace width="2.2762em"/></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover><mo>←</mo><msub><mi>v</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>c</mi><mi>e</mi><mi>n</mi><mi>t</mi><mi>e</mi><mi>r</mi><mi>e</mi><mi>d</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msubsup><mi>g</mi><mi>t</mi><mrow><mi>a</mi><mi>v</mi><mi>e</mi></mrow></msubsup><mo>←</mo><msubsup><mi>g</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mrow><mi>a</mi><mi>v</mi><mi>e</mi></mrow></msubsup><mi>α</mi><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>α</mi><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover><mo>←</mo><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover><mo>−</mo><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msubsup><mi>g</mi><mi>t</mi><mrow><mi>a</mi><mi>v</mi><mi>e</mi></mrow></msubsup><msup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo><mn>2</mn></msup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>μ</mi><mo>&gt;</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub><mo>←</mo><mi>μ</mi><msub><mtext mathvariant="bold">b</mtext><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><msub><mi>g</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>e</mi><mi>l</mi><mi>s</mi><mi>e</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><msub><mi>g</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo><mspace width="0.8536em"/></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4516,7 +4516,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4530,7 +4530,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4583,7 +4583,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4617,7 +4617,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4654,7 +4654,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4686,7 +4686,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4718,7 +4718,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4741,7 +4741,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4766,7 +4766,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4829,7 +4829,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rmsprop.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rmsprop.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4841,7 +4841,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.RMSprop.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.RMSprop.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.Rprop.html b/2.9/generated/torch.optim.Rprop.html
index 239f21a9a7d..7957c16a54a 100644
--- a/2.9/generated/torch.optim.Rprop.html
+++ b/2.9/generated/torch.optim.Rprop.html
@@ -4404,7 +4404,7 @@
 <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.Rprop">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Rprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.5,</span> <span class="pre">1.2)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(1e-06,</span> <span class="pre">50)</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rprop.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Rprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.5,</span> <span class="pre">1.2)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(1e-06,</span> <span class="pre">50)</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rprop.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements the resilient backpropagation algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><msub><mi>θ</mi><mn>0</mn></msub><mo>∈</mo><msup><mi mathvariant="bold">R</mi><mi>d</mi></msup><mtext> (params)</mtext><mo separator="true">,</mo><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><msub><mi>η</mi><mrow><mo>+</mo><mi mathvariant="normal">/</mi><mo>−</mo></mrow></msub><mtext> (etaplus, etaminus)</mtext><mo separator="true">,</mo><msub><mi mathvariant="normal">Γ</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi><mi mathvariant="normal">/</mi><mi>m</mi><mi>i</mi><mi>n</mi></mrow></msub><mtext> (step sizes)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msubsup><mi>g</mi><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>v</mi></mrow><mn>0</mn></msubsup><mo>←</mo><mn>0</mn><mo separator="true">,</mo><mtext> </mtext><msub><mi>η</mi><mn>0</mn></msub><mo>←</mo><mtext>lr (learning rate)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>i</mi><mo>=</mo><mn>0</mn><mo separator="true">,</mo><mn>1</mn><mo separator="true">,</mo><mo>…</mo><mo separator="true">,</mo><mi>d</mi><mo>−</mo><mn>1</mn><mtext> </mtext><mrow><mi mathvariant="bold">d</mi><mi mathvariant="bold">o</mi></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><msubsup><mi>g</mi><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>v</mi></mrow><mi>i</mi></msubsup><msubsup><mi>g</mi><mi>t</mi><mi>i</mi></msubsup><mo>&gt;</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msubsup><mi>η</mi><mi>t</mi><mi>i</mi></msubsup><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">i</mi><mi mathvariant="normal">n</mi></mrow><mo stretchy="false">(</mo><msubsup><mi>η</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mi>i</mi></msubsup><msub><mi>η</mi><mo lspace="0em" rspace="0em">+</mo></msub><mo separator="true">,</mo><msub><mi mathvariant="normal">Γ</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mrow><mtext mathvariant="bold">else</mtext><mtext> </mtext><mtext mathvariant="bold">if</mtext></mrow><mtext> </mtext><msubsup><mi>g</mi><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>v</mi></mrow><mi>i</mi></msubsup><msubsup><mi>g</mi><mi>t</mi><mi>i</mi></msubsup><mo>&lt;</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msubsup><mi>η</mi><mi>t</mi><mi>i</mi></msubsup><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">a</mi><mi mathvariant="normal">x</mi></mrow><mo stretchy="false">(</mo><msubsup><mi>η</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mi>i</mi></msubsup><msub><mi>η</mi><mo lspace="0em" rspace="0em">−</mo></msub><mo separator="true">,</mo><msub><mi mathvariant="normal">Γ</mi><mrow><mi>m</mi><mi>i</mi><mi>n</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msubsup><mi>g</mi><mi>t</mi><mi>i</mi></msubsup><mo>←</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">else</mtext><mtext> </mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msubsup><mi>η</mi><mi>t</mi><mi>i</mi></msubsup><mo>←</mo><msubsup><mi>η</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mi>i</mi></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><msub><mi>η</mi><mi>t</mi></msub><mrow><mi mathvariant="normal">s</mi><mi mathvariant="normal">i</mi><mi mathvariant="normal">g</mi><mi mathvariant="normal">n</mi></mrow><mo stretchy="false">(</mo><msub><mi>g</mi><mi>t</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>v</mi></mrow></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4473,7 +4473,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4487,7 +4487,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4540,7 +4540,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4574,7 +4574,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4611,7 +4611,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4643,7 +4643,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4675,7 +4675,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4698,7 +4698,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4723,7 +4723,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4786,7 +4786,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rprop.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rprop.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4798,7 +4798,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.Rprop.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Rprop.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.SGD.html b/2.9/generated/torch.optim.SGD.html
index 0e0388ff677..55d11553655 100644
--- a/2.9/generated/torch.optim.SGD.html
+++ b/2.9/generated/torch.optim.SGD.html
@@ -4404,7 +4404,7 @@
 <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.SGD">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">SGD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dampening</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nesterov</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sgd.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">SGD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dampening</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nesterov</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sgd.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements stochastic gradient descent (optionally with momentum).</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mtext> </mtext><mi>μ</mi><mtext> (momentum)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>τ</mi><mtext> (dampening)</mtext><mo separator="true">,</mo><mtext> </mtext><mrow><mtext> </mtext><mtext mathvariant="italic">nesterov,</mtext></mrow><mtext> </mtext><mrow><mtext> </mtext><mtext mathvariant="italic">maximize</mtext></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>μ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>t</mi><mo>&gt;</mo><mn>1</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub><mo>←</mo><mi>μ</mi><msub><mtext mathvariant="bold">b</mtext><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>τ</mi><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">nesterov</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>μ</mi><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4518,7 +4518,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4532,7 +4532,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4585,7 +4585,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4619,7 +4619,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4656,7 +4656,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4688,7 +4688,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4720,7 +4720,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4743,7 +4743,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4768,7 +4768,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4831,7 +4831,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sgd.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sgd.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4843,7 +4843,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SGD.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SGD.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.SparseAdam.html b/2.9/generated/torch.optim.SparseAdam.html
index df88602daec..475b0ab70c0 100644
--- a/2.9/generated/torch.optim.SparseAdam.html
+++ b/2.9/generated/torch.optim.SparseAdam.html
@@ -4404,7 +4404,7 @@
 <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">SparseAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sparse_adam.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">SparseAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sparse_adam.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam" title="Permalink to this definition">#</a></dt>
 <dd><p>SparseAdam implements a masked version of the Adam algorithm
 suitable for sparse gradients. Currently, due to implementation constraints (explained
 below), SparseAdam is only intended for a narrow subset of use cases, specifically
@@ -4463,7 +4463,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code></a> as training progresses.</p>
@@ -4477,7 +4477,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4530,7 +4530,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4564,7 +4564,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4601,7 +4601,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4633,7 +4633,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4665,7 +4665,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4688,7 +4688,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4713,7 +4713,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4776,7 +4776,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sparse_adam.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sparse_adam.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4788,7 +4788,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.SparseAdam.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.SparseAdam.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.adadelta.Adadelta.html b/2.9/generated/torch.optim.adadelta.Adadelta.html
index 73a11e41b82..c3dc7fa3e3e 100644
--- a/2.9/generated/torch.optim.adadelta.Adadelta.html
+++ b/2.9/generated/torch.optim.adadelta.Adadelta.html
@@ -4415,7 +4415,7 @@
 <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adadelta.</span></span><span class="sig-name descname"><span class="pre">Adadelta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rho</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.9</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adadelta.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adadelta.</span></span><span class="sig-name descname"><span class="pre">Adadelta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rho</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.9</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-06</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adadelta.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Adadelta algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>ρ</mi><mtext> (decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> </mtext><mtext> (square avg)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>u</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> </mtext><mtext> (accumulate variables)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mi>ρ</mi><mo>+</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>ρ</mi><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi mathvariant="normal">Δ</mi><msub><mi>x</mi><mi>t</mi></msub><mo>←</mo><mfrac><msqrt><mrow><msub><mi>u</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mi>ϵ</mi></mrow></msqrt><msqrt><mrow><msub><mi>v</mi><mi>t</mi></msub><mo>+</mo><mi>ϵ</mi></mrow></msqrt></mfrac><msub><mi>g</mi><mi>t</mi></msub><mspace width="5.9751em"/></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>u</mi><mi>t</mi></msub><mo>←</mo><msub><mi>u</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mi>ρ</mi><mo>+</mo><mi mathvariant="normal">Δ</mi><msubsup><mi>x</mi><mi>t</mi><mn>2</mn></msubsup><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>ρ</mi><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><mi mathvariant="normal">Δ</mi><msub><mi>x</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4503,7 +4503,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4517,7 +4517,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4570,7 +4570,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4604,7 +4604,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4641,7 +4641,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4673,7 +4673,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4705,7 +4705,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4728,7 +4728,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4753,7 +4753,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4816,7 +4816,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adadelta.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adadelta.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4828,7 +4828,7 @@ <h1>Adadelta<a class="headerlink" href="#adadelta" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adadelta.Adadelta.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.Adadelta.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.adadelta.adadelta.html b/2.9/generated/torch.optim.adadelta.adadelta.html
index f3f7c292555..34e00240883 100644
--- a/2.9/generated/torch.optim.adadelta.adadelta.html
+++ b/2.9/generated/torch.optim.adadelta.adadelta.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.adadelta.adadelta<a class="headerlink" href="#torch-optim-adadelta-adadelta" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.adadelta.adadelta">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.adadelta.</span></span><span class="sig-name descname"><span class="pre">adadelta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">square_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">acc_deltas</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rho</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adadelta.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.adadelta" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.adadelta.</span></span><span class="sig-name descname"><span class="pre">adadelta</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">square_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">acc_deltas</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rho</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adadelta.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adadelta.adadelta" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs Adadelta algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.Adadelta.html#torch.optim.Adadelta" title="torch.optim.Adadelta"><code class="xref py py-class docutils literal notranslate"><span class="pre">Adadelta</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.adagrad.Adagrad.html b/2.9/generated/torch.optim.adagrad.Adagrad.html
index e2ee9f73e8e..0337d4c5d07 100644
--- a/2.9/generated/torch.optim.adagrad.Adagrad.html
+++ b/2.9/generated/torch.optim.adagrad.Adagrad.html
@@ -4415,7 +4415,7 @@
 <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adagrad.</span></span><span class="sig-name descname"><span class="pre">Adagrad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">initial_accumulator_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adagrad.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adagrad.</span></span><span class="sig-name descname"><span class="pre">Adagrad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">initial_accumulator_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adagrad.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Adagrad algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><mi>τ</mi><mtext> (initial accumulator value)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>η</mi><mtext> (lr decay)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><mi>s</mi><mi>t</mi><mi>a</mi><mi>t</mi><mi>e</mi><mi mathvariant="normal">_</mi><mi>s</mi><mi>u</mi><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mi>τ</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><mi>γ</mi><mo>~</mo></mover><mo>←</mo><mi>γ</mi><mi mathvariant="normal">/</mi><mo stretchy="false">(</mo><mn>1</mn><mo>+</mo><mo stretchy="false">(</mo><mi>t</mi><mo>−</mo><mn>1</mn><mo stretchy="false">)</mo><mi>η</mi><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>s</mi><mi>t</mi><mi>a</mi><mi>t</mi><mi>e</mi><mi mathvariant="normal">_</mi><mi>s</mi><mi>u</mi><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><mi>s</mi><mi>t</mi><mi>a</mi><mi>t</mi><mi>e</mi><mi mathvariant="normal">_</mi><mi>s</mi><mi>u</mi><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mover accent="true"><mi>γ</mi><mo>~</mo></mover><mfrac><msub><mi>g</mi><mi>t</mi></msub><mrow><msqrt><mrow><mi>s</mi><mi>t</mi><mi>a</mi><mi>t</mi><mi>e</mi><mi mathvariant="normal">_</mi><mi>s</mi><mi>u</mi><msub><mi>m</mi><mi>t</mi></msub></mrow></msqrt><mo>+</mo><mi>ϵ</mi></mrow></mfrac></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4486,7 +4486,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4500,7 +4500,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4553,7 +4553,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4587,7 +4587,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4624,7 +4624,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4656,7 +4656,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4688,7 +4688,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4711,7 +4711,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4736,13 +4736,13 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.share_memory">
-<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adagrad.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.share_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adagrad.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.share_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>Calls tensor.share_memory_() on the state sum tensors.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4805,7 +4805,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adagrad.py#L147"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adagrad.py#L147"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4817,7 +4817,7 @@ <h1>Adagrad<a class="headerlink" href="#adagrad" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adagrad.Adagrad.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.Adagrad.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.adagrad.adagrad.html b/2.9/generated/torch.optim.adagrad.adagrad.html
index 0c4c70edb30..ac215b7e756 100644
--- a/2.9/generated/torch.optim.adagrad.adagrad.html
+++ b/2.9/generated/torch.optim.adagrad.adagrad.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.adagrad.adagrad<a class="headerlink" href="#torch-optim-adagrad-adagrad" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.adagrad.adagrad">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.adagrad.</span></span><span class="sig-name descname"><span class="pre">adagrad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_sums</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">found_inf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_sparse_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adagrad.py#L244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.adagrad" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.adagrad.</span></span><span class="sig-name descname"><span class="pre">adagrad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_sums</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">found_inf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_sparse_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adagrad.py#L244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adagrad.adagrad" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs Adagrad algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.Adagrad.html#torch.optim.Adagrad" title="torch.optim.Adagrad"><code class="xref py py-class docutils literal notranslate"><span class="pre">Adagrad</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.adam.Adam.html b/2.9/generated/torch.optim.adam.Adam.html
index 91f32bc60e8..852ca18d131 100644
--- a/2.9/generated/torch.optim.adam.Adam.html
+++ b/2.9/generated/torch.optim.adam.Adam.html
@@ -4415,7 +4415,7 @@
 <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adam.</span></span><span class="sig-name descname"><span class="pre">Adam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adam.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adam.</span></span><span class="sig-name descname"><span class="pre">Adam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adam.py#L34"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Adam algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext> (betas)</mtext><mo separator="true">,</mo><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">amsgrad</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo separator="true">,</mo><mtext> </mtext><mi>ϵ</mi><mtext> (epsilon)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( first moment)</mtext><mo separator="true">,</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> (second moment)</mtext><mo separator="true">,</mo><mtext> </mtext><msubsup><mi>v</mi><mn>0</mn><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo>←</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>m</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>1</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>a</mi><mi>m</mi><mi>s</mi><mi>g</mi><mi>r</mi><mi>a</mi><mi>d</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msubsup><mi>v</mi><mi>t</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">a</mi><mi mathvariant="normal">x</mi></mrow><mo stretchy="false">(</mo><msubsup><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo separator="true">,</mo><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msubsup><mi>v</mi><mi>t</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>v</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4526,7 +4526,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4540,7 +4540,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4593,7 +4593,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4627,7 +4627,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4664,7 +4664,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4696,7 +4696,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4728,7 +4728,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4751,7 +4751,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4776,7 +4776,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4839,7 +4839,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adam.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adam.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4851,7 +4851,7 @@ <h1>Adam<a class="headerlink" href="#adam" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adam.Adam.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.Adam.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.adam.adam.html b/2.9/generated/torch.optim.adam.adam.html
index 156e2d5294f..0a4cbfcbfa8 100644
--- a/2.9/generated/torch.optim.adam.adam.html
+++ b/2.9/generated/torch.optim.adam.adam.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.adam.adam<a class="headerlink" href="#torch-optim-adam-adam" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.adam.adam">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.adam.</span></span><span class="sig-name descname"><span class="pre">adam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">found_inf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adam.py#L885"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.adam" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.adam.</span></span><span class="sig-name descname"><span class="pre">adam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">found_inf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adam.py#L885"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adam.adam" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs Adam algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.Adam.html#torch.optim.Adam" title="torch.optim.Adam"><code class="xref py py-class docutils literal notranslate"><span class="pre">Adam</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.adamax.Adamax.html b/2.9/generated/torch.optim.adamax.Adamax.html
index 9c079e96bfd..cfc5c7f95ef 100644
--- a/2.9/generated/torch.optim.adamax.Adamax.html
+++ b/2.9/generated/torch.optim.adamax.Adamax.html
@@ -4415,7 +4415,7 @@
 <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adamax.</span></span><span class="sig-name descname"><span class="pre">Adamax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.002</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adamax.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adamax.</span></span><span class="sig-name descname"><span class="pre">Adamax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.002</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adamax.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Adamax algorithm (a variant of Adam based on infinity norm).</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext> (betas)</mtext><mo separator="true">,</mo><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>ϵ</mi><mtext> (epsilon)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( first moment)</mtext><mo separator="true">,</mo><msub><mi>u</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( infinity norm)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>u</mi><mi>t</mi></msub><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">a</mi><mi mathvariant="normal">x</mi></mrow><mo stretchy="false">(</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>u</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo separator="true">,</mo><mi mathvariant="normal">∣</mi><msub><mi>g</mi><mi>t</mi></msub><mi mathvariant="normal">∣</mi><mo>+</mo><mi>ϵ</mi><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mfrac><mrow><mi>γ</mi><msub><mi>m</mi><mi>t</mi></msub></mrow><mrow><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>1</mn><mi>t</mi></msubsup><mo stretchy="false">)</mo><msub><mi>u</mi><mi>t</mi></msub></mrow></mfrac></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4476,7 +4476,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4490,7 +4490,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4543,7 +4543,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4577,7 +4577,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4614,7 +4614,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4646,7 +4646,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4678,7 +4678,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4701,7 +4701,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4726,7 +4726,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4789,7 +4789,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adamax.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adamax.py#L122"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4801,7 +4801,7 @@ <h1>Adamax<a class="headerlink" href="#adamax" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamax.Adamax.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.Adamax.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.adamax.adamax.html b/2.9/generated/torch.optim.adamax.adamax.html
index 6a07d89246c..cfb21bc43e9 100644
--- a/2.9/generated/torch.optim.adamax.adamax.html
+++ b/2.9/generated/torch.optim.adamax.adamax.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.adamax.adamax<a class="headerlink" href="#torch-optim-adamax-adamax" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.adamax.adamax">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.adamax.</span></span><span class="sig-name descname"><span class="pre">adamax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_infs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adamax.py#L421"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.adamax" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.adamax.</span></span><span class="sig-name descname"><span class="pre">adamax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_infs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adamax.py#L421"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamax.adamax" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs adamax algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.Adamax.html#torch.optim.Adamax" title="torch.optim.Adamax"><code class="xref py py-class docutils literal notranslate"><span class="pre">Adamax</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.adamw.AdamW.html b/2.9/generated/torch.optim.adamw.AdamW.html
index 5a66aa3e0be..4d702dc7175 100644
--- a/2.9/generated/torch.optim.adamw.AdamW.html
+++ b/2.9/generated/torch.optim.adamw.AdamW.html
@@ -4415,7 +4415,7 @@
 <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adamw.</span></span><span class="sig-name descname"><span class="pre">AdamW</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adamw.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.adamw.</span></span><span class="sig-name descname"><span class="pre">AdamW</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adamw.py#L21"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements AdamW algorithm, where weight decay does not accumulate in the momentum nor variance.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext>(lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext>(betas)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext>(params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext>(objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>ϵ</mi><mtext> (epsilon)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>λ</mi><mtext>(weight decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">amsgrad</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">maximize</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> (first moment)</mtext><mo separator="true">,</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( second moment)</mtext><mo separator="true">,</mo><mtext> </mtext><msubsup><mi>v</mi><mn>0</mn><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo>←</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>m</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>1</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>a</mi><mi>m</mi><mi>s</mi><mi>g</mi><mi>r</mi><mi>a</mi><mi>d</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msubsup><mi>v</mi><mi>t</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">a</mi><mi mathvariant="normal">x</mi></mrow><mo stretchy="false">(</mo><msubsup><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mo separator="true">,</mo><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msubsup><mi>v</mi><mi>t</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msubsup><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>v</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4523,7 +4523,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4537,7 +4537,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4590,7 +4590,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4624,7 +4624,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4661,7 +4661,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4693,7 +4693,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4725,7 +4725,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4748,7 +4748,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4773,7 +4773,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4836,7 +4836,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adam.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adam.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4848,7 +4848,7 @@ <h1>AdamW<a class="headerlink" href="#adamw" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.adamw.AdamW.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.AdamW.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.adamw.adamw.html b/2.9/generated/torch.optim.adamw.adamw.html
index 6b46418a96a..86d1fd2f183 100644
--- a/2.9/generated/torch.optim.adamw.adamw.html
+++ b/2.9/generated/torch.optim.adamw.adamw.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.adamw.adamw<a class="headerlink" href="#torch-optim-adamw-adamw" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.adamw.adamw">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.adamw.</span></span><span class="sig-name descname"><span class="pre">adamw</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">found_inf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/adamw.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.adamw" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.adamw.</span></span><span class="sig-name descname"><span class="pre">adamw</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">found_inf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">amsgrad</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/adamw.py#L130"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.adamw.adamw" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs AdamW algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.AdamW.html#torch.optim.AdamW" title="torch.optim.AdamW"><code class="xref py py-class docutils literal notranslate"><span class="pre">AdamW</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.asgd.ASGD.html b/2.9/generated/torch.optim.asgd.ASGD.html
index e2d51a4d10c..34a21582934 100644
--- a/2.9/generated/torch.optim.asgd.ASGD.html
+++ b/2.9/generated/torch.optim.asgd.ASGD.html
@@ -4415,7 +4415,7 @@
 <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.asgd.</span></span><span class="sig-name descname"><span class="pre">ASGD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t0</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000000.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/asgd.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.asgd.</span></span><span class="sig-name descname"><span class="pre">ASGD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lambd</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.75</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t0</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000000.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/asgd.py#L29"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements Averaged Stochastic Gradient Descent.</p>
 <p>It has been proposed in <a class="reference external" href="https://meyn.ece.ufl.edu/wp-content/uploads/sites/77/archive/spm_files/Courses/ECE555-2011/555media/poljud92.pdf">Acceleration of stochastic approximation by
 averaging</a>.</p>
@@ -4454,7 +4454,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4468,7 +4468,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4521,7 +4521,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4555,7 +4555,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4592,7 +4592,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4624,7 +4624,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4656,7 +4656,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4679,7 +4679,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4704,7 +4704,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4767,7 +4767,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/asgd.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/asgd.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4779,7 +4779,7 @@ <h1>ASGD<a class="headerlink" href="#asgd" title="Permalink to this heading">#</
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.asgd.ASGD.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.ASGD.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.asgd.asgd.html b/2.9/generated/torch.optim.asgd.asgd.html
index b678ace4967..3ca59e9ec1a 100644
--- a/2.9/generated/torch.optim.asgd.asgd.html
+++ b/2.9/generated/torch.optim.asgd.asgd.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.asgd.asgd<a class="headerlink" href="#torch-optim-asgd-asgd" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.asgd.asgd">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.asgd.</span></span><span class="sig-name descname"><span class="pre">asgd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">axs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mus</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etas</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lambd</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/asgd.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.asgd" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.asgd.</span></span><span class="sig-name descname"><span class="pre">asgd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">axs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mus</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etas</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lambd</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/asgd.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.asgd.asgd" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs asgd algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.ASGD.html#torch.optim.ASGD" title="torch.optim.ASGD"><code class="xref py py-class docutils literal notranslate"><span class="pre">ASGD</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.lbfgs.LBFGS.html b/2.9/generated/torch.optim.lbfgs.LBFGS.html
index 956b293361f..efdc8c16349 100644
--- a/2.9/generated/torch.optim.lbfgs.LBFGS.html
+++ b/2.9/generated/torch.optim.lbfgs.LBFGS.html
@@ -4415,7 +4415,7 @@
 <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lbfgs.</span></span><span class="sig-name descname"><span class="pre">LBFGS</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_eval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tolerance_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tolerance_change</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-09</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">history_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">line_search_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lbfgs.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lbfgs.</span></span><span class="sig-name descname"><span class="pre">LBFGS</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_iter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_eval</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tolerance_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-07</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tolerance_change</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-09</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">history_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">line_search_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lbfgs.py#L183"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements L-BFGS algorithm.</p>
 <p>Heavily inspired by <a class="reference external" href="https://www.cs.ubc.ca/~schmidtm/Software/minFunc.html">minFunc</a>.</p>
 <div class="admonition warning">
@@ -4454,7 +4454,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4468,7 +4468,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4521,7 +4521,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4555,7 +4555,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4592,7 +4592,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4624,7 +4624,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4656,7 +4656,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4679,7 +4679,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4704,7 +4704,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4767,7 +4767,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lbfgs.py#L301"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lbfgs.py#L301"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4779,7 +4779,7 @@ <h1>LBFGS<a class="headerlink" href="#lbfgs" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lbfgs.LBFGS.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lbfgs.LBFGS.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.lr_scheduler.ChainedScheduler.html b/2.9/generated/torch.optim.lr_scheduler.ChainedScheduler.html
index d2712aa599a..af8380a7176 100644
--- a/2.9/generated/torch.optim.lr_scheduler.ChainedScheduler.html
+++ b/2.9/generated/torch.optim.lr_scheduler.ChainedScheduler.html
@@ -4404,7 +4404,7 @@
 <h1>ChainedScheduler<a class="headerlink" href="#chainedscheduler" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ChainedScheduler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">ChainedScheduler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">schedulers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">ChainedScheduler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">schedulers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimizer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler" title="Permalink to this definition">#</a></dt>
 <dd><p>Chains a list of learning rate schedulers.</p>
 <p>Takes in a sequence of chainable learning rate schedulers and calls their
 step() functions consecutively in just one call to step().</p>
@@ -4437,7 +4437,7 @@ <h1>ChainedScheduler<a class="headerlink" href="#chainedscheduler" title="Permal
 <img alt="../_images/ChainedScheduler.png" src="../_images/ChainedScheduler.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ChainedScheduler.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4448,7 +4448,7 @@ <h1>ChainedScheduler<a class="headerlink" href="#chainedscheduler" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ChainedScheduler.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute learning rate using chainable form of the scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4459,7 +4459,7 @@ <h1>ChainedScheduler<a class="headerlink" href="#chainedscheduler" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ChainedScheduler.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1217"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4471,7 +4471,7 @@ <h1>ChainedScheduler<a class="headerlink" href="#chainedscheduler" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ChainedScheduler.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1197"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.
@@ -4485,7 +4485,7 @@ <h1>ChainedScheduler<a class="headerlink" href="#chainedscheduler" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ChainedScheduler.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1189"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ChainedScheduler.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.ConstantLR.html b/2.9/generated/torch.optim.lr_scheduler.ConstantLR.html
index 991c225b2b6..a6c2dcd1afa 100644
--- a/2.9/generated/torch.optim.lr_scheduler.ConstantLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.ConstantLR.html
@@ -4404,7 +4404,7 @@
 <h1>ConstantLR<a class="headerlink" href="#constantlr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ConstantLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">ConstantLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3333333333333333</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_iters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L595"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">ConstantLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3333333333333333</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_iters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L595"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Multiply the learning rate of each parameter group by a small constant factor.</p>
 <p>The multiplication is done until the number of epoch reaches a pre-defined milestone: total_iters.
 Notice that such multiplication of the small constant factor can
@@ -4439,7 +4439,7 @@ <h1>ConstantLR<a class="headerlink" href="#constantlr" title="Permalink to this
 <img alt="../_images/ConstantLR.png" src="../_images/ConstantLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ConstantLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4450,7 +4450,7 @@ <h1>ConstantLR<a class="headerlink" href="#constantlr" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ConstantLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L644"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L644"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the learning rate of each parameter group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4461,7 +4461,7 @@ <h1>ConstantLR<a class="headerlink" href="#constantlr" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ConstantLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4473,7 +4473,7 @@ <h1>ConstantLR<a class="headerlink" href="#constantlr" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ConstantLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4486,7 +4486,7 @@ <h1>ConstantLR<a class="headerlink" href="#constantlr" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ConstantLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ConstantLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.CosineAnnealingLR.html b/2.9/generated/torch.optim.lr_scheduler.CosineAnnealingLR.html
index 0de1ca8086a..9efc5ba2072 100644
--- a/2.9/generated/torch.optim.lr_scheduler.CosineAnnealingLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.CosineAnnealingLR.html
@@ -4404,7 +4404,7 @@
 <h1>CosineAnnealingLR<a class="headerlink" href="#cosineannealinglr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">CosineAnnealingLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">T_max</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eta_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">CosineAnnealingLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">T_max</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eta_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the learning rate of each parameter group using a cosine annealing schedule.</p>
 <p>The learning rate is updated recursively using:</p>
 <div class="math">
@@ -4452,7 +4452,7 @@ <h1>CosineAnnealingLR<a class="headerlink" href="#cosineannealinglr" title="Perm
 <img alt="../_images/CosineAnnealingLR.png" src="../_images/CosineAnnealingLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4463,7 +4463,7 @@ <h1>CosineAnnealingLR<a class="headerlink" href="#cosineannealinglr" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1087"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1087"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Retrieve the learning rate of each parameter group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4474,7 +4474,7 @@ <h1>CosineAnnealingLR<a class="headerlink" href="#cosineannealinglr" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4486,7 +4486,7 @@ <h1>CosineAnnealingLR<a class="headerlink" href="#cosineannealinglr" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4499,7 +4499,7 @@ <h1>CosineAnnealingLR<a class="headerlink" href="#cosineannealinglr" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.html b/2.9/generated/torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.html
index 057a7e1cc8d..387dc5a4e66 100644
--- a/2.9/generated/torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.html
+++ b/2.9/generated/torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.html
@@ -4404,7 +4404,7 @@
 <h1>CosineAnnealingWarmRestarts<a class="headerlink" href="#cosineannealingwarmrestarts" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingWarmRestarts">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">CosineAnnealingWarmRestarts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">T_0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">T_mult</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eta_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">CosineAnnealingWarmRestarts</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">T_0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">T_mult</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eta_min</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the learning rate of each parameter group using a cosine annealing schedule.</p>
 <p>The <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>η</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msub></mrow><annotation encoding="application/x-tex">\eta_{max}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.1944em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">η</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.1514em;"><span style="top:-2.55em;margin-left:-0.0359em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">ma</span><span class="mord mathnormal mtight">x</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> is set to the initial lr, <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>T</mi><mrow><mi>c</mi><mi>u</mi><mi>r</mi></mrow></msub></mrow><annotation encoding="application/x-tex">T_{cur}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">T</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.1514em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">c</span><span class="mord mathnormal mtight">u</span><span class="mord mathnormal mtight" style="margin-right:0.02778em;">r</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>
 is the number of epochs since the last restart and <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>T</mi><mi>i</mi></msub></mrow><annotation encoding="application/x-tex">T_{i}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.8333em;vertical-align:-0.15em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">T</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.3117em;"><span style="top:-2.55em;margin-left:-0.1389em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">i</span></span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span> is the number
@@ -4442,7 +4442,7 @@ <h1>CosineAnnealingWarmRestarts<a class="headerlink" href="#cosineannealingwarmr
 <img alt="../_images/CosineAnnealingWarmRestarts.png" src="../_images/CosineAnnealingWarmRestarts.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4453,7 +4453,7 @@ <h1>CosineAnnealingWarmRestarts<a class="headerlink" href="#cosineannealingwarmr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1788"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1788"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the initial learning rate.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4464,7 +4464,7 @@ <h1>CosineAnnealingWarmRestarts<a class="headerlink" href="#cosineannealingwarmr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4476,7 +4476,7 @@ <h1>CosineAnnealingWarmRestarts<a class="headerlink" href="#cosineannealingwarmr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4489,7 +4489,7 @@ <h1>CosineAnnealingWarmRestarts<a class="headerlink" href="#cosineannealingwarmr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1801"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1801"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CosineAnnealingWarmRestarts.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Step could be called after every batch update.</p>
 <p class="rubric">Example</p>
 <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">scheduler</span> <span class="o">=</span> <span class="n">CosineAnnealingWarmRestarts</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">T_0</span><span class="p">,</span> <span class="n">T_mult</span><span class="p">)</span>
diff --git a/2.9/generated/torch.optim.lr_scheduler.CyclicLR.html b/2.9/generated/torch.optim.lr_scheduler.CyclicLR.html
index 52c068e10ad..e9bc39c7aa4 100644
--- a/2.9/generated/torch.optim.lr_scheduler.CyclicLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.CyclicLR.html
@@ -4404,7 +4404,7 @@
 <h1>CyclicLR<a class="headerlink" href="#cycliclr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CyclicLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">CyclicLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">base_lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size_up</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size_down</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'triangular'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gamma</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cycle'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cycle_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">base_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.9</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1432"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">CyclicLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">base_lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size_up</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2000</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size_down</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'triangular'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gamma</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cycle'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cycle_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">base_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.9</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1432"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the learning rate of each parameter group according to cyclical learning rate policy (CLR).</p>
 <p>The policy cycles the learning rate between two boundaries with a constant frequency,
 as detailed in the paper <a class="reference external" href="https://arxiv.org/abs/1506.01186">Cyclical Learning Rates for Training Neural Networks</a>.
@@ -4500,7 +4500,7 @@ <h1>CyclicLR<a class="headerlink" href="#cycliclr" title="Permalink to this head
 <img alt="../_images/CyclicLR.png" src="../_images/CyclicLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CyclicLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4511,7 +4511,7 @@ <h1>CyclicLR<a class="headerlink" href="#cycliclr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CyclicLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1642"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1642"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Calculate the learning rate at batch index.</p>
 <p>This function treats <cite>self.last_epoch</cite> as the last batch index.</p>
 <p>If <cite>self.cycle_momentum</cite> is <code class="docutils literal notranslate"><span class="pre">True</span></code>, this function has a side effect of
@@ -4525,7 +4525,7 @@ <h1>CyclicLR<a class="headerlink" href="#cycliclr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CyclicLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1714"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1714"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 </dl>
@@ -4533,7 +4533,7 @@ <h1>CyclicLR<a class="headerlink" href="#cycliclr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CyclicLR.scale_fn">
-<span class="sig-name descname"><span class="pre">scale_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1623"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.scale_fn" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">scale_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1623"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.scale_fn" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the scaling policy.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4544,7 +4544,7 @@ <h1>CyclicLR<a class="headerlink" href="#cycliclr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CyclicLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1690"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1690"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.
@@ -4560,7 +4560,7 @@ <h1>CyclicLR<a class="headerlink" href="#cycliclr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.CyclicLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.CyclicLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.ExponentialLR.html b/2.9/generated/torch.optim.lr_scheduler.ExponentialLR.html
index 0d6582ac030..01a9c08cb78 100644
--- a/2.9/generated/torch.optim.lr_scheduler.ExponentialLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.ExponentialLR.html
@@ -4404,7 +4404,7 @@
 <h1>ExponentialLR<a class="headerlink" href="#exponentiallr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ExponentialLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">ExponentialLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gamma</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L765"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">ExponentialLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gamma</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L765"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Decays the learning rate of each parameter group by gamma every epoch.</p>
 <p>When last_epoch=-1, sets initial lr as lr.</p>
 <dl class="field-list simple">
@@ -4427,7 +4427,7 @@ <h1>ExponentialLR<a class="headerlink" href="#exponentiallr" title="Permalink to
 <img alt="../_images/ExponentialLR.png" src="../_images/ExponentialLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ExponentialLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4438,7 +4438,7 @@ <h1>ExponentialLR<a class="headerlink" href="#exponentiallr" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ExponentialLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L795"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L795"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the learning rate of each parameter group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4449,7 +4449,7 @@ <h1>ExponentialLR<a class="headerlink" href="#exponentiallr" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ExponentialLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4461,7 +4461,7 @@ <h1>ExponentialLR<a class="headerlink" href="#exponentiallr" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ExponentialLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4474,7 +4474,7 @@ <h1>ExponentialLR<a class="headerlink" href="#exponentiallr" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ExponentialLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ExponentialLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.LRScheduler.html b/2.9/generated/torch.optim.lr_scheduler.LRScheduler.html
index 74f453e8991..8933d4445b4 100644
--- a/2.9/generated/torch.optim.lr_scheduler.LRScheduler.html
+++ b/2.9/generated/torch.optim.lr_scheduler.LRScheduler.html
@@ -4404,13 +4404,13 @@
 <h1>LRScheduler<a class="headerlink" href="#lrscheduler" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LRScheduler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">LRScheduler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">LRScheduler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler" title="Permalink to this definition">#</a></dt>
 <dd><p>Adjusts the learning rate during optimization.</p>
 <dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LRScheduler.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4421,7 +4421,7 @@ <h1>LRScheduler<a class="headerlink" href="#lrscheduler" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LRScheduler.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute learning rate using chainable form of the scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4432,7 +4432,7 @@ <h1>LRScheduler<a class="headerlink" href="#lrscheduler" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LRScheduler.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4444,7 +4444,7 @@ <h1>LRScheduler<a class="headerlink" href="#lrscheduler" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LRScheduler.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4457,7 +4457,7 @@ <h1>LRScheduler<a class="headerlink" href="#lrscheduler" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LRScheduler.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LRScheduler.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.LambdaLR.html b/2.9/generated/torch.optim.lr_scheduler.LambdaLR.html
index 878c9efe0b8..8b88dd1ed86 100644
--- a/2.9/generated/torch.optim.lr_scheduler.LambdaLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.LambdaLR.html
@@ -4404,7 +4404,7 @@
 <h1>LambdaLR<a class="headerlink" href="#lambdalr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LambdaLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">LambdaLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_lambda</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L269"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">LambdaLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_lambda</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L269"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the initial learning rate.</p>
 <p>The learning rate of each parameter group is set to the initial lr
 times a given function. When last_epoch=-1, sets initial lr as lr.</p>
@@ -4441,7 +4441,7 @@ <h1>LambdaLR<a class="headerlink" href="#lambdalr" title="Permalink to this head
 <img alt="../_images/LambdaLR.png" src="../_images/LambdaLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LambdaLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4452,7 +4452,7 @@ <h1>LambdaLR<a class="headerlink" href="#lambdalr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LambdaLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L367"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L367"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute learning rate.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4463,7 +4463,7 @@ <h1>LambdaLR<a class="headerlink" href="#lambdalr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LambdaLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L347"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L347"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <p>When saving or loading the scheduler, please make sure to also save or load the state of the optimizer.</p>
 <dl class="field-list simple">
@@ -4476,7 +4476,7 @@ <h1>LambdaLR<a class="headerlink" href="#lambdalr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LambdaLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L323"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L323"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.
@@ -4492,7 +4492,7 @@ <h1>LambdaLR<a class="headerlink" href="#lambdalr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LambdaLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LambdaLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.LinearLR.html b/2.9/generated/torch.optim.lr_scheduler.LinearLR.html
index b26dab09693..9c8f681f8cd 100644
--- a/2.9/generated/torch.optim.lr_scheduler.LinearLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.LinearLR.html
@@ -4404,7 +4404,7 @@
 <h1>LinearLR<a class="headerlink" href="#linearlr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LinearLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">LinearLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3333333333333333</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_iters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">LinearLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3333333333333333</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">end_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_iters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Decays the learning rate of each parameter group by linearly changing small multiplicative factor.</p>
 <p>The multiplication is done until the number of epoch reaches a pre-defined milestone: total_iters.
 Notice that such decay can happen simultaneously with other changes to the learning rate
@@ -4442,7 +4442,7 @@ <h1>LinearLR<a class="headerlink" href="#linearlr" title="Permalink to this head
 <img alt="../_images/LinearLR.png" src="../_images/LinearLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LinearLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4453,7 +4453,7 @@ <h1>LinearLR<a class="headerlink" href="#linearlr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LinearLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L726"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L726"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the learning rate.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4464,7 +4464,7 @@ <h1>LinearLR<a class="headerlink" href="#linearlr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LinearLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4476,7 +4476,7 @@ <h1>LinearLR<a class="headerlink" href="#linearlr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LinearLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4489,7 +4489,7 @@ <h1>LinearLR<a class="headerlink" href="#linearlr" title="Permalink to this head
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.LinearLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.LinearLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.MultiStepLR.html b/2.9/generated/torch.optim.lr_scheduler.MultiStepLR.html
index a73370df55e..953f0f280eb 100644
--- a/2.9/generated/torch.optim.lr_scheduler.MultiStepLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.MultiStepLR.html
@@ -4404,7 +4404,7 @@
 <h1>MultiStepLR<a class="headerlink" href="#multisteplr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiStepLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">MultiStepLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">milestones</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gamma</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L536"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">MultiStepLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">milestones</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gamma</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L536"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Decays the learning rate of each parameter group by gamma once the number of epoch reaches one of the milestones.</p>
 <p>Notice that such decay can happen simultaneously with other changes to the learning rate
 from outside this scheduler. When last_epoch=-1, sets initial lr as lr.</p>
@@ -4434,7 +4434,7 @@ <h1>MultiStepLR<a class="headerlink" href="#multisteplr" title="Permalink to thi
 <img alt="../_images/MultiStepLR.png" src="../_images/MultiStepLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiStepLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4445,7 +4445,7 @@ <h1>MultiStepLR<a class="headerlink" href="#multisteplr" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiStepLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L575"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the learning rate of each parameter group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4456,7 +4456,7 @@ <h1>MultiStepLR<a class="headerlink" href="#multisteplr" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiStepLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4468,7 +4468,7 @@ <h1>MultiStepLR<a class="headerlink" href="#multisteplr" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiStepLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4481,7 +4481,7 @@ <h1>MultiStepLR<a class="headerlink" href="#multisteplr" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiStepLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiStepLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.MultiplicativeLR.html b/2.9/generated/torch.optim.lr_scheduler.MultiplicativeLR.html
index 329d6c6a429..7c1d4e4d590 100644
--- a/2.9/generated/torch.optim.lr_scheduler.MultiplicativeLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.MultiplicativeLR.html
@@ -4404,7 +4404,7 @@
 <h1>MultiplicativeLR<a class="headerlink" href="#multiplicativelr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiplicativeLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">MultiplicativeLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_lambda</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L378"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">MultiplicativeLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr_lambda</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L378"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Multiply the learning rate of each parameter group by the factor given in the specified function.</p>
 <p>When last_epoch=-1, set initial lr as lr.</p>
 <dl class="field-list simple">
@@ -4430,7 +4430,7 @@ <h1>MultiplicativeLR<a class="headerlink" href="#multiplicativelr" title="Permal
 <img alt="../_images/MultiplicativeLR.png" src="../_images/MultiplicativeLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiplicativeLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4441,7 +4441,7 @@ <h1>MultiplicativeLR<a class="headerlink" href="#multiplicativelr" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiplicativeLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L466"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L466"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the learning rate of each parameter group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4452,7 +4452,7 @@ <h1>MultiplicativeLR<a class="headerlink" href="#multiplicativelr" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiplicativeLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4464,7 +4464,7 @@ <h1>MultiplicativeLR<a class="headerlink" href="#multiplicativelr" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiplicativeLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.
@@ -4479,7 +4479,7 @@ <h1>MultiplicativeLR<a class="headerlink" href="#multiplicativelr" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.MultiplicativeLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.MultiplicativeLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.OneCycleLR.html b/2.9/generated/torch.optim.lr_scheduler.OneCycleLR.html
index 79e925945ad..cbe39a54734 100644
--- a/2.9/generated/torch.optim.lr_scheduler.OneCycleLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.OneCycleLR.html
@@ -4404,7 +4404,7 @@
 <h1>OneCycleLR<a class="headerlink" href="#onecyclelr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.OneCycleLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">OneCycleLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_steps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">epochs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">steps_per_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pct_start</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">anneal_strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cos'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cycle_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">base_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.85</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.95</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">div_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">25.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_div_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10000.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">three_phase</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1874"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">OneCycleLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_steps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">epochs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">steps_per_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pct_start</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">anneal_strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cos'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cycle_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">base_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.85</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.95</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">div_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">25.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">final_div_factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10000.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">three_phase</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1874"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the learning rate of each parameter group according to the 1cycle learning rate policy.</p>
 <p>The 1cycle policy anneals the learning rate from an initial learning rate to some maximum
 learning rate and then from that maximum learning rate to some minimum learning rate much
@@ -4503,7 +4503,7 @@ <h1>OneCycleLR<a class="headerlink" href="#onecyclelr" title="Permalink to this
 <img alt="../_images/OneCycleLR.png" src="../_images/OneCycleLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.OneCycleLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4514,7 +4514,7 @@ <h1>OneCycleLR<a class="headerlink" href="#onecyclelr" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.OneCycleLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L2134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L2134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the learning rate of each parameter group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4525,7 +4525,7 @@ <h1>OneCycleLR<a class="headerlink" href="#onecyclelr" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.OneCycleLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4537,7 +4537,7 @@ <h1>OneCycleLR<a class="headerlink" href="#onecyclelr" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.OneCycleLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4550,7 +4550,7 @@ <h1>OneCycleLR<a class="headerlink" href="#onecyclelr" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.OneCycleLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.OneCycleLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.PolynomialLR.html b/2.9/generated/torch.optim.lr_scheduler.PolynomialLR.html
index c20025d33d9..30b8631cfcf 100644
--- a/2.9/generated/torch.optim.lr_scheduler.PolynomialLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.PolynomialLR.html
@@ -4404,7 +4404,7 @@
 <h1>PolynomialLR<a class="headerlink" href="#polynomiallr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.PolynomialLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">PolynomialLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_iters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">power</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">PolynomialLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">total_iters</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">5</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">power</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Decays the learning rate of each parameter group using a polynomial function in the given total_iters.</p>
 <p>When last_epoch=-1, sets initial lr as lr.</p>
 <dl class="field-list simple">
@@ -4433,7 +4433,7 @@ <h1>PolynomialLR<a class="headerlink" href="#polynomiallr" title="Permalink to t
 <img alt="../_images/PolynomialLR.png" src="../_images/PolynomialLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.PolynomialLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4444,7 +4444,7 @@ <h1>PolynomialLR<a class="headerlink" href="#polynomiallr" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.PolynomialLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1001"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1001"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the learning rate.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4455,7 +4455,7 @@ <h1>PolynomialLR<a class="headerlink" href="#polynomiallr" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.PolynomialLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4467,7 +4467,7 @@ <h1>PolynomialLR<a class="headerlink" href="#polynomiallr" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.PolynomialLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4480,7 +4480,7 @@ <h1>PolynomialLR<a class="headerlink" href="#polynomiallr" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.PolynomialLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.PolynomialLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html b/2.9/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html
index 3988472549e..1013b17cc95 100644
--- a/2.9/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html
+++ b/2.9/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html
@@ -4404,7 +4404,7 @@
 <h1>ReduceLROnPlateau<a class="headerlink" href="#reducelronplateau" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ReduceLROnPlateau">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">ReduceLROnPlateau</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'min'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">patience</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'rel'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cooldown</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1235"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">ReduceLROnPlateau</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'min'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">factor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">patience</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'rel'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cooldown</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1235"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau" title="Permalink to this definition">#</a></dt>
 <dd><p>Reduce learning rate when a metric has stopped improving.</p>
 <p>Models often benefit from reducing the learning rate by a factor
 of 2-10 once learning stagnates. This scheduler reads a metrics
@@ -4463,7 +4463,7 @@ <h1>ReduceLROnPlateau<a class="headerlink" href="#reducelronplateau" title="Perm
 <img alt="../_images/ReduceLROnPlateau.png" src="../_images/ReduceLROnPlateau.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ReduceLROnPlateau.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4474,7 +4474,7 @@ <h1>ReduceLROnPlateau<a class="headerlink" href="#reducelronplateau" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ReduceLROnPlateau.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute learning rate using chainable form of the scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4485,7 +4485,7 @@ <h1>ReduceLROnPlateau<a class="headerlink" href="#reducelronplateau" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ReduceLROnPlateau.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1423"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1423"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 </dl>
@@ -4493,7 +4493,7 @@ <h1>ReduceLROnPlateau<a class="headerlink" href="#reducelronplateau" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ReduceLROnPlateau.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4506,7 +4506,7 @@ <h1>ReduceLROnPlateau<a class="headerlink" href="#reducelronplateau" title="Perm
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.ReduceLROnPlateau.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metrics</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L1340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">metrics</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L1340"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.ReduceLROnPlateau.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.SequentialLR.html b/2.9/generated/torch.optim.lr_scheduler.SequentialLR.html
index cbb862a09d3..321f06c6627 100644
--- a/2.9/generated/torch.optim.lr_scheduler.SequentialLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.SequentialLR.html
@@ -4404,7 +4404,7 @@
 <h1>SequentialLR<a class="headerlink" href="#sequentiallr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.SequentialLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">SequentialLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schedulers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">milestones</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L810"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">SequentialLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schedulers</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">milestones</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L810"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Contains a list of schedulers expected to be called sequentially during the optimization process.</p>
 <p>Specifically, the schedulers will be called according to the milestone points, which should provide exact
 intervals by which each scheduler should be called at a given epoch.</p>
@@ -4443,7 +4443,7 @@ <h1>SequentialLR<a class="headerlink" href="#sequentiallr" title="Permalink to t
 <img alt="../_images/SequentialLR.png" src="../_images/SequentialLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.SequentialLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4454,7 +4454,7 @@ <h1>SequentialLR<a class="headerlink" href="#sequentiallr" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.SequentialLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute learning rate using chainable form of the scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4465,7 +4465,7 @@ <h1>SequentialLR<a class="headerlink" href="#sequentiallr" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.SequentialLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L945"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L945"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4477,14 +4477,14 @@ <h1>SequentialLR<a class="headerlink" href="#sequentiallr" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.SequentialLR.recursive_undo">
-<span class="sig-name descname"><span class="pre">recursive_undo</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sched</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L900"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.recursive_undo" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">recursive_undo</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sched</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L900"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.recursive_undo" title="Permalink to this definition">#</a></dt>
 <dd><p>Recursively undo any step performed by the initialisation of
 schedulers.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.SequentialLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L925"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L925"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.
@@ -4498,7 +4498,7 @@ <h1>SequentialLR<a class="headerlink" href="#sequentiallr" title="Permalink to t
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.SequentialLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L913"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L913"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.SequentialLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.lr_scheduler.StepLR.html b/2.9/generated/torch.optim.lr_scheduler.StepLR.html
index 902454f78a8..c749692c40e 100644
--- a/2.9/generated/torch.optim.lr_scheduler.StepLR.html
+++ b/2.9/generated/torch.optim.lr_scheduler.StepLR.html
@@ -4404,7 +4404,7 @@
 <h1>StepLR<a class="headerlink" href="#steplr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.StepLR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">StepLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gamma</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L480"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.lr_scheduler.</span></span><span class="sig-name descname"><span class="pre">StepLR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gamma</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L480"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR" title="Permalink to this definition">#</a></dt>
 <dd><p>Decays the learning rate of each parameter group by gamma every step_size epochs.</p>
 <p>Notice that such decay can happen simultaneously with other changes to the learning rate
 from outside this scheduler. When last_epoch=-1, sets initial lr as lr.</p>
@@ -4435,7 +4435,7 @@ <h1>StepLR<a class="headerlink" href="#steplr" title="Permalink to this heading"
 <img alt="../_images/StepLR.png" src="../_images/StepLR.png" />
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.StepLR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4446,7 +4446,7 @@ <h1>StepLR<a class="headerlink" href="#steplr" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.StepLR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L520"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the learning rate of each parameter group.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4457,7 +4457,7 @@ <h1>StepLR<a class="headerlink" href="#steplr" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.StepLR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4469,7 +4469,7 @@ <h1>StepLR<a class="headerlink" href="#steplr" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.StepLR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4482,7 +4482,7 @@ <h1>StepLR<a class="headerlink" href="#steplr" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.lr_scheduler.StepLR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.lr_scheduler.StepLR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.optim.nadam.NAdam.html b/2.9/generated/torch.optim.nadam.NAdam.html
index 78819683bb1..ed5ba59d7ff 100644
--- a/2.9/generated/torch.optim.nadam.NAdam.html
+++ b/2.9/generated/torch.optim.nadam.NAdam.html
@@ -4415,7 +4415,7 @@
 <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.nadam.</span></span><span class="sig-name descname"><span class="pre">NAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.002</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.004</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/nadam.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.nadam.</span></span><span class="sig-name descname"><span class="pre">NAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.002</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.004</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/nadam.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements NAdam algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><msub><mi>γ</mi><mi>t</mi></msub><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext> (betas)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>ψ</mi><mtext> (momentum decay)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mtext> </mtext><mtext mathvariant="italic">decoupled_weight_decay</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">maximize</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( first moment)</mtext><mo separator="true">,</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( second moment)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">decoupled_weight_decay</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>μ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><mfrac><mn>1</mn><mn>2</mn></mfrac><msup><mn>0.96</mn><mrow><mi>t</mi><mi>ψ</mi></mrow></msup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>μ</mi><mrow><mi>t</mi><mo>+</mo><mn>1</mn></mrow></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><mfrac><mn>1</mn><mn>2</mn></mfrac><msup><mn>0.96</mn><mrow><mo stretchy="false">(</mo><mi>t</mi><mo>+</mo><mn>1</mn><mo stretchy="false">)</mo><mi>ψ</mi></mrow></msup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>μ</mi><mrow><mi>t</mi><mo>+</mo><mn>1</mn></mrow></msub><msub><mi>m</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><munderover><mo>∏</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mrow><mi>t</mi><mo>+</mo><mn>1</mn></mrow></munderover><msub><mi>μ</mi><mi>i</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.1298em"/><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>μ</mi><mi>t</mi></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><munderover><mo>∏</mo><mrow><mi>i</mi><mo>=</mo><mn>1</mn></mrow><mi>t</mi></munderover><msub><mi>μ</mi><mi>i</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>v</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4507,7 +4507,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4521,7 +4521,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4574,7 +4574,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4608,7 +4608,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4645,7 +4645,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4677,7 +4677,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4709,7 +4709,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4732,7 +4732,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4757,7 +4757,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4820,7 +4820,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/nadam.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/nadam.py#L156"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4832,7 +4832,7 @@ <h1>NAdam<a class="headerlink" href="#nadam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.nadam.NAdam.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.NAdam.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.nadam.nadam.html b/2.9/generated/torch.optim.nadam.nadam.html
index 64cae11a71c..3d55dd4a7fb 100644
--- a/2.9/generated/torch.optim.nadam.nadam.html
+++ b/2.9/generated/torch.optim.nadam.nadam.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.nadam.nadam<a class="headerlink" href="#torch-optim-nadam-nadam" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.nadam.nadam">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.nadam.</span></span><span class="sig-name descname"><span class="pre">nadam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mu_products</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/nadam.py#L599"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.nadam" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.nadam.</span></span><span class="sig-name descname"><span class="pre">nadam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mu_products</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/nadam.py#L599"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.nadam.nadam" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs NAdam algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.NAdam.html#torch.optim.NAdam" title="torch.optim.NAdam"><code class="xref py py-class docutils literal notranslate"><span class="pre">NAdam</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.radam.RAdam.html b/2.9/generated/torch.optim.radam.RAdam.html
index 2d9fef653e7..8810c1950d8 100644
--- a/2.9/generated/torch.optim.radam.RAdam.html
+++ b/2.9/generated/torch.optim.radam.RAdam.html
@@ -4415,7 +4415,7 @@
 <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.radam.</span></span><span class="sig-name descname"><span class="pre">RAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/radam.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.radam.</span></span><span class="sig-name descname"><span class="pre">RAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/radam.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements RAdam algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>β</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>β</mi><mn>2</mn></msub><mtext> (betas)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weightdecay)</mtext><mo separator="true">,</mo><mtext> </mtext><mtext mathvariant="italic">maximize</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>ϵ</mi><mtext> (epsilon)</mtext><mo separator="true">,</mo><mtext mathvariant="italic">decoupled_weight_decay</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>m</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( first moment)</mtext><mo separator="true">,</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> ( second moment)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="5.1215em"/><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub><mo>←</mo><mn>2</mn><mi mathvariant="normal">/</mi><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><mo>−</mo><mn>1</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">decoupled_weight_decay</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="5.1215em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mi>λ</mi><msub><mi>θ</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="5.1215em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><msub><mi>m</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>1</mn></msub><msub><mi>m</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>1</mn></msub><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><msub><mi>β</mi><mn>2</mn></msub><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msub><mi>β</mi><mn>2</mn></msub><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><mo>←</mo><msub><mi>m</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>1</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><msub><mi>ρ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub><mo>−</mo><mn>2</mn><mi>t</mi><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><msub><mi>ρ</mi><mi>t</mi></msub><mo>&gt;</mo><mn>5</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>l</mi><mi>t</mi></msub><mo>←</mo><mfrac><msqrt><mrow><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><msubsup><mi>β</mi><mn>2</mn><mi>t</mi></msubsup><mo stretchy="false">)</mo></mrow></msqrt><mrow><msqrt><msub><mi>v</mi><mi>t</mi></msub></msqrt><mo>+</mo><mi>ϵ</mi></mrow></mfrac></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>r</mi><mi>t</mi></msub><mo>←</mo><msqrt><mfrac><mrow><mo stretchy="false">(</mo><msub><mi>ρ</mi><mi>t</mi></msub><mo>−</mo><mn>4</mn><mo stretchy="false">)</mo><mo stretchy="false">(</mo><msub><mi>ρ</mi><mi>t</mi></msub><mo>−</mo><mn>2</mn><mo stretchy="false">)</mo><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub></mrow><mrow><mo stretchy="false">(</mo><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub><mo>−</mo><mn>4</mn><mo stretchy="false">)</mo><mo stretchy="false">(</mo><msub><mi>ρ</mi><mi mathvariant="normal">∞</mi></msub><mo>−</mo><mn>2</mn><mo stretchy="false">)</mo><msub><mi>ρ</mi><mi>t</mi></msub></mrow></mfrac></msqrt></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover><msub><mi>r</mi><mi>t</mi></msub><msub><mi>l</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.7072em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.4143em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mi>t</mi></msub><mo>−</mo><mi>γ</mi><mover accent="true"><msub><mi>m</mi><mi>t</mi></msub><mo stretchy="true">^</mo></mover></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4533,7 +4533,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4547,7 +4547,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4600,7 +4600,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4634,7 +4634,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4671,7 +4671,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4703,7 +4703,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4735,7 +4735,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4758,7 +4758,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4783,7 +4783,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4846,7 +4846,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/radam.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/radam.py#L127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4858,7 +4858,7 @@ <h1>RAdam<a class="headerlink" href="#radam" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.radam.RAdam.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.RAdam.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.radam.radam.html b/2.9/generated/torch.optim.radam.radam.html
index 3d151221298..118a1667f61 100644
--- a/2.9/generated/torch.optim.radam.radam.html
+++ b/2.9/generated/torch.optim.radam.radam.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.radam.radam<a class="headerlink" href="#torch-optim-radam-radam" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.radam.radam">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.radam.</span></span><span class="sig-name descname"><span class="pre">radam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/radam.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.radam" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.radam.</span></span><span class="sig-name descname"><span class="pre">radam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exp_avg_sqs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">decoupled_weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/radam.py#L559"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.radam.radam" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs RAdam algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.RAdam.html#torch.optim.RAdam" title="torch.optim.RAdam"><code class="xref py py-class docutils literal notranslate"><span class="pre">RAdam</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.rmsprop.RMSprop.html b/2.9/generated/torch.optim.rmsprop.RMSprop.html
index 8d1b3272ce7..d4449bccfae 100644
--- a/2.9/generated/torch.optim.rmsprop.RMSprop.html
+++ b/2.9/generated/torch.optim.rmsprop.RMSprop.html
@@ -4415,7 +4415,7 @@
 <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.rmsprop.</span></span><span class="sig-name descname"><span class="pre">RMSprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.99</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">centered</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rmsprop.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.rmsprop.</span></span><span class="sig-name descname"><span class="pre">RMSprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.99</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">centered</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rmsprop.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements RMSprop algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>α</mi><mtext> (alpha)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>μ</mi><mtext> (momentum)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>c</mi><mi>e</mi><mi>n</mi><mi>t</mi><mi>e</mi><mi>r</mi><mi>e</mi><mi>d</mi><mo separator="true">,</mo><mtext> </mtext><mi>ϵ</mi><mtext> (epsilon)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msub><mi>v</mi><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> (square average)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mtext mathvariant="bold">b</mtext><mn>0</mn></msub><mo>←</mo><mn>0</mn><mtext> (buffer)</mtext><mo separator="true">,</mo><mtext> </mtext><msubsup><mi>g</mi><mn>0</mn><mrow><mi>a</mi><mi>v</mi><mi>e</mi></mrow></msubsup><mo>←</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>v</mi><mi>t</mi></msub><mo>←</mo><mi>α</mi><msub><mi>v</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>α</mi><mo stretchy="false">)</mo><msubsup><mi>g</mi><mi>t</mi><mn>2</mn></msubsup><mspace width="2.2762em"/></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover><mo>←</mo><msub><mi>v</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>c</mi><mi>e</mi><mi>n</mi><mi>t</mi><mi>e</mi><mi>r</mi><mi>e</mi><mi>d</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msubsup><mi>g</mi><mi>t</mi><mrow><mi>a</mi><mi>v</mi><mi>e</mi></mrow></msubsup><mo>←</mo><msubsup><mi>g</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mrow><mi>a</mi><mi>v</mi><mi>e</mi></mrow></msubsup><mi>α</mi><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>α</mi><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover><mo>←</mo><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover><mo>−</mo><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msubsup><mi>g</mi><mi>t</mi><mrow><mi>a</mi><mi>v</mi><mi>e</mi></mrow></msubsup><msup><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo><mn>2</mn></msup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>i</mi><mi>f</mi><mtext> </mtext><mi>μ</mi><mo>&gt;</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub><mo>←</mo><mi>μ</mi><msub><mtext mathvariant="bold">b</mtext><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><msub><mi>g</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mi>e</mi><mi>l</mi><mi>s</mi><mi>e</mi></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><msub><mi>g</mi><mi>t</mi></msub><mi mathvariant="normal">/</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">(</mo><msqrt><mover accent="true"><msub><mi>v</mi><mi>t</mi></msub><mo>~</mo></mover></msqrt><mo>+</mo><mi>ϵ</mi><mo fence="false" stretchy="true" minsize="1.2em" maxsize="1.2em">)</mo><mspace width="0.8536em"/></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4527,7 +4527,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4541,7 +4541,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4594,7 +4594,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4628,7 +4628,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4665,7 +4665,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4697,7 +4697,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4729,7 +4729,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4752,7 +4752,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4777,7 +4777,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4840,7 +4840,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rmsprop.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rmsprop.py#L144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4852,7 +4852,7 @@ <h1>RMSprop<a class="headerlink" href="#rmsprop" title="Permalink to this headin
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.RMSprop.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.RMSprop.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.rmsprop.rmsprop.html b/2.9/generated/torch.optim.rmsprop.rmsprop.html
index ffd96773e58..e1bb38edf24 100644
--- a/2.9/generated/torch.optim.rmsprop.rmsprop.html
+++ b/2.9/generated/torch.optim.rmsprop.rmsprop.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.rmsprop.rmsprop<a class="headerlink" href="#torch-optim-rmsprop-rmsprop" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.rmsprop.rmsprop">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.rmsprop.</span></span><span class="sig-name descname"><span class="pre">rmsprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">square_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_buffer_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">centered</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rmsprop.py#L473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.rmsprop" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.rmsprop.</span></span><span class="sig-name descname"><span class="pre">rmsprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">square_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_avgs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_buffer_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">centered</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rmsprop.py#L473"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rmsprop.rmsprop" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs rmsprop algorithm computation.</p>
 <p>See <code class="xref py py-class docutils literal notranslate"><span class="pre">RMSProp</span></code> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.rprop.Rprop.html b/2.9/generated/torch.optim.rprop.Rprop.html
index 996f70d6cee..8ab391d426f 100644
--- a/2.9/generated/torch.optim.rprop.Rprop.html
+++ b/2.9/generated/torch.optim.rprop.Rprop.html
@@ -4415,7 +4415,7 @@
 <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.rprop.</span></span><span class="sig-name descname"><span class="pre">Rprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.5,</span> <span class="pre">1.2)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(1e-06,</span> <span class="pre">50)</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rprop.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.rprop.</span></span><span class="sig-name descname"><span class="pre">Rprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.5,</span> <span class="pre">1.2)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_sizes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(1e-06,</span> <span class="pre">50)</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rprop.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements the resilient backpropagation algorithm.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><msub><mi>θ</mi><mn>0</mn></msub><mo>∈</mo><msup><mi mathvariant="bold">R</mi><mi>d</mi></msup><mtext> (params)</mtext><mo separator="true">,</mo><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><msub><mi>η</mi><mrow><mo>+</mo><mi mathvariant="normal">/</mi><mo>−</mo></mrow></msub><mtext> (etaplus, etaminus)</mtext><mo separator="true">,</mo><msub><mi mathvariant="normal">Γ</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi><mi mathvariant="normal">/</mi><mi>m</mi><mi>i</mi><mi>n</mi></mrow></msub><mtext> (step sizes)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">initialize</mtext><mo>:</mo><msubsup><mi>g</mi><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>v</mi></mrow><mn>0</mn></msubsup><mo>←</mo><mn>0</mn><mo separator="true">,</mo><mtext> </mtext><msub><mi>η</mi><mn>0</mn></msub><mo>←</mo><mtext>lr (learning rate)</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>i</mi><mo>=</mo><mn>0</mn><mo separator="true">,</mo><mn>1</mn><mo separator="true">,</mo><mo>…</mo><mo separator="true">,</mo><mi>d</mi><mo>−</mo><mn>1</mn><mtext> </mtext><mrow><mi mathvariant="bold">d</mi><mi mathvariant="bold">o</mi></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><msubsup><mi>g</mi><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>v</mi></mrow><mi>i</mi></msubsup><msubsup><mi>g</mi><mi>t</mi><mi>i</mi></msubsup><mo>&gt;</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msubsup><mi>η</mi><mi>t</mi><mi>i</mi></msubsup><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">i</mi><mi mathvariant="normal">n</mi></mrow><mo stretchy="false">(</mo><msubsup><mi>η</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mi>i</mi></msubsup><msub><mi>η</mi><mo lspace="0em" rspace="0em">+</mo></msub><mo separator="true">,</mo><msub><mi mathvariant="normal">Γ</mi><mrow><mi>m</mi><mi>a</mi><mi>x</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mrow><mtext mathvariant="bold">else</mtext><mtext> </mtext><mtext mathvariant="bold">if</mtext></mrow><mtext> </mtext><msubsup><mi>g</mi><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>v</mi></mrow><mi>i</mi></msubsup><msubsup><mi>g</mi><mi>t</mi><mi>i</mi></msubsup><mo>&lt;</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msubsup><mi>η</mi><mi>t</mi><mi>i</mi></msubsup><mo>←</mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">a</mi><mi mathvariant="normal">x</mi></mrow><mo stretchy="false">(</mo><msubsup><mi>η</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mi>i</mi></msubsup><msub><mi>η</mi><mo lspace="0em" rspace="0em">−</mo></msub><mo separator="true">,</mo><msub><mi mathvariant="normal">Γ</mi><mrow><mi>m</mi><mi>i</mi><mi>n</mi></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msubsup><mi>g</mi><mi>t</mi><mi>i</mi></msubsup><mo>←</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">else</mtext><mtext> </mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msubsup><mi>η</mi><mi>t</mi><mi>i</mi></msubsup><mo>←</mo><msubsup><mi>η</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow><mi>i</mi></msubsup></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><msub><mi>η</mi><mi>t</mi></msub><mrow><mi mathvariant="normal">s</mi><mi mathvariant="normal">i</mi><mi mathvariant="normal">g</mi><mi mathvariant="normal">n</mi></mrow><mo stretchy="false">(</mo><msub><mi>g</mi><mi>t</mi></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>g</mi><mrow><mi>p</mi><mi>r</mi><mi>e</mi><mi>v</mi></mrow></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4484,7 +4484,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4498,7 +4498,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4551,7 +4551,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4585,7 +4585,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4622,7 +4622,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4654,7 +4654,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4686,7 +4686,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4709,7 +4709,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4734,7 +4734,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4797,7 +4797,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rprop.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rprop.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4809,7 +4809,7 @@ <h1>Rprop<a class="headerlink" href="#rprop" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.rprop.Rprop.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.Rprop.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.rprop.rprop.html b/2.9/generated/torch.optim.rprop.rprop.html
index acbfddb03cf..51365c17644 100644
--- a/2.9/generated/torch.optim.rprop.rprop.html
+++ b/2.9/generated/torch.optim.rprop.rprop.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.rprop.rprop<a class="headerlink" href="#torch-optim-rprop-rprop" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.rprop.rprop">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.rprop.</span></span><span class="sig-name descname"><span class="pre">rprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prevs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_sizes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size_min</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size_max</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etaminus</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etaplus</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/rprop.py#L409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.rprop" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.rprop.</span></span><span class="sig-name descname"><span class="pre">rprop</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grads</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prevs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_sizes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_steps</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">capturable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size_min</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">step_size_max</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etaminus</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">etaplus</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/rprop.py#L409"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.rprop.rprop" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs rprop algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.Rprop.html#torch.optim.Rprop" title="torch.optim.Rprop"><code class="xref py py-class docutils literal notranslate"><span class="pre">Rprop</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.sgd.SGD.html b/2.9/generated/torch.optim.sgd.SGD.html
index efc666c8501..51f657d34ae 100644
--- a/2.9/generated/torch.optim.sgd.SGD.html
+++ b/2.9/generated/torch.optim.sgd.SGD.html
@@ -4415,7 +4415,7 @@
 <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.sgd.</span></span><span class="sig-name descname"><span class="pre">SGD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dampening</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nesterov</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sgd.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.sgd.</span></span><span class="sig-name descname"><span class="pre">SGD</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dampening</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nesterov</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">differentiable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sgd.py#L28"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements stochastic gradient descent (optionally with momentum).</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mtable rowspacing="0.25em" columnalign="right left" columnspacing="0em"><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">input</mtext><mo>:</mo><mi>γ</mi><mtext> (lr)</mtext><mo separator="true">,</mo><mtext> </mtext><msub><mi>θ</mi><mn>0</mn></msub><mtext> (params)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>f</mi><mo stretchy="false">(</mo><mi>θ</mi><mo stretchy="false">)</mo><mtext> (objective)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>λ</mi><mtext> (weight decay)</mtext><mo separator="true">,</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="3.6989em"/><mtext> </mtext><mi>μ</mi><mtext> (momentum)</mtext><mo separator="true">,</mo><mtext> </mtext><mi>τ</mi><mtext> (dampening)</mtext><mo separator="true">,</mo><mtext> </mtext><mrow><mtext> </mtext><mtext mathvariant="italic">nesterov,</mtext></mrow><mtext> </mtext><mrow><mtext> </mtext><mtext mathvariant="italic">maximize</mtext></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mtext mathvariant="bold">for</mtext><mtext> </mtext><mi>t</mi><mo>=</mo><mn>1</mn><mtext> </mtext><mtext mathvariant="bold">to</mtext><mtext> </mtext><mo>…</mo><mtext> </mtext><mtext mathvariant="bold">do</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">maximize</mtext><mo>:</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><mo>−</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi mathvariant="normal">∇</mi><mi>θ</mi></msub><msub><mi>f</mi><mi>t</mi></msub><mo stretchy="false">(</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo stretchy="false">)</mo></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>λ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>λ</mi><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>μ</mi><mo mathvariant="normal">≠</mo><mn>0</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mi>t</mi><mo>&gt;</mo><mn>1</mn></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub><mo>←</mo><mi>μ</mi><msub><mtext mathvariant="bold">b</mtext><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>+</mo><mo stretchy="false">(</mo><mn>1</mn><mo>−</mo><mi>τ</mi><mo stretchy="false">)</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">if</mtext><mtext> </mtext><mtext mathvariant="italic">nesterov</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mi>g</mi><mi>t</mi></msub><mo>+</mo><mi>μ</mi><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="2.8453em"/><mtext mathvariant="bold">else</mtext></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="4.2679em"/><msub><mi>g</mi><mi>t</mi></msub><mo>←</mo><msub><mtext mathvariant="bold">b</mtext><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mspace width="1.4226em"/><msub><mi>θ</mi><mi>t</mi></msub><mo>←</mo><msub><mi>θ</mi><mrow><mi>t</mi><mo>−</mo><mn>1</mn></mrow></msub><mo>−</mo><mi>γ</mi><msub><mi>g</mi><mi>t</mi></msub></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mrow><mrow><mi mathvariant="bold">r</mi><mi mathvariant="bold">e</mi><mi mathvariant="bold">t</mi><mi mathvariant="bold">u</mi><mi mathvariant="bold">r</mi><mi mathvariant="bold">n</mi></mrow><mtext> </mtext><msub><mi mathvariant="bold">θ</mi><mi mathvariant="bold">t</mi></msub></mrow></mrow></mstyle></mtd></mtr><mtr><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow></mrow></mstyle></mtd><mtd><mstyle scriptlevel="0" displaystyle="true"><mrow><mrow></mrow><mpadded height="0em" voffset="0em"><mspace mathbackground="black" width="31.298em" height="0.04em"></mspace></mpadded></mrow></mstyle></mtd></mtr></mtable><annotation encoding="application/x-tex">\begin{aligned}
@@ -4529,7 +4529,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4543,7 +4543,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4596,7 +4596,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4630,7 +4630,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4667,7 +4667,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4699,7 +4699,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4731,7 +4731,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4754,7 +4754,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4779,7 +4779,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4842,7 +4842,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sgd.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sgd.py#L105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4854,7 +4854,7 @@ <h1>SGD<a class="headerlink" href="#sgd" title="Permalink to this heading">#</a>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sgd.SGD.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.SGD.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.sgd.sgd.html b/2.9/generated/torch.optim.sgd.sgd.html
index 8a902e5ed35..93006fbdee5 100644
--- a/2.9/generated/torch.optim.sgd.sgd.html
+++ b/2.9/generated/torch.optim.sgd.sgd.html
@@ -4415,7 +4415,7 @@
 <h1>torch.optim.sgd.sgd<a class="headerlink" href="#torch-optim-sgd-sgd" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.sgd.sgd">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.sgd.</span></span><span class="sig-name descname"><span class="pre">sgd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">d_p_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_buffer_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_sparse_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">found_inf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dampening</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nesterov</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sgd.py#L250"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.sgd" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.sgd.</span></span><span class="sig-name descname"><span class="pre">sgd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">d_p_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum_buffer_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">has_sparse_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">foreach</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fused</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grad_scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">found_inf</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weight_decay</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">momentum</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dampening</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nesterov</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sgd.py#L250"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sgd.sgd" title="Permalink to this definition">#</a></dt>
 <dd><p>Functional API that performs SGD algorithm computation.</p>
 <p>See <a class="reference internal" href="torch.optim.SGD.html#torch.optim.SGD" title="torch.optim.SGD"><code class="xref py py-class docutils literal notranslate"><span class="pre">SGD</span></code></a> for details.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.sparse_adam.SparseAdam.html b/2.9/generated/torch.optim.sparse_adam.SparseAdam.html
index b31ab96eb06..d481a021fd7 100644
--- a/2.9/generated/torch.optim.sparse_adam.SparseAdam.html
+++ b/2.9/generated/torch.optim.sparse_adam.SparseAdam.html
@@ -4415,7 +4415,7 @@
 <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.sparse_adam.</span></span><span class="sig-name descname"><span class="pre">SparseAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sparse_adam.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.sparse_adam.</span></span><span class="sig-name descname"><span class="pre">SparseAdam</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lr</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.001</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">betas</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(0.9,</span> <span class="pre">0.999)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">eps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1e-08</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sparse_adam.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam" title="Permalink to this definition">#</a></dt>
 <dd><p>SparseAdam implements a masked version of the Adam algorithm
 suitable for sparse gradients. Currently, due to implementation constraints (explained
 below), SparseAdam is only intended for a narrow subset of use cases, specifically
@@ -4474,7 +4474,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.add_param_group">
-<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.add_param_group" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_param_group</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">param_group</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L1069"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.add_param_group" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a param group to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> s <cite>param_groups</cite>.</p>
 <p>This can be useful when fine tuning a pre-trained network as frozen layers can be made
 trainable and added to the <code class="xref py py-class docutils literal notranslate"><span class="pre">Optimizer</span></code> as training progresses.</p>
@@ -4488,7 +4488,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L866"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the optimizer state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4541,7 +4541,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L830"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict post-hook which will be called after
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4575,7 +4575,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L791"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a load_state_dict pre-hook which will be called before
 <a class="reference internal" href="torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict" title="torch.optim.Optimizer.load_state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> is called. It should have the
 following signature:</p>
@@ -4612,7 +4612,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L633"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict post-hook which will be called after <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">state_dict</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">state_dict</span> <span class="ow">or</span> <span class="kc">None</span>
@@ -4644,7 +4644,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L601"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a state dict pre-hook which will be called before <a class="reference internal" href="torch.optim.Optimizer.state_dict.html#torch.optim.Optimizer.state_dict" title="torch.optim.Optimizer.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> is called.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4676,7 +4676,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.register_step_post_hook">
-<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L580"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_step_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step post hook which will be called after optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span>
@@ -4699,7 +4699,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.register_step_pre_hook">
-<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_step_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L557"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.register_step_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an optimizer step pre hook which will be called before optimizer step.</p>
 <p>It should have the following signature:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">hook</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">modified</span> <span class="n">args</span> <span class="ow">and</span> <span class="n">kwargs</span>
@@ -4724,7 +4724,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the optimizer as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains two entries:</p>
 <ul class="simple">
@@ -4787,7 +4787,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/sparse_adam.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">closure</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/sparse_adam.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a single optimization step.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4799,7 +4799,7 @@ <h1>SparseAdam<a class="headerlink" href="#sparseadam" title="Permalink to this
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.sparse_adam.SparseAdam.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L997"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.sparse_adam.SparseAdam.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the gradients of all optimized <a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> s.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.optim.swa_utils.AveragedModel.html b/2.9/generated/torch.optim.swa_utils.AveragedModel.html
index 57261475995..512251422b3 100644
--- a/2.9/generated/torch.optim.swa_utils.AveragedModel.html
+++ b/2.9/generated/torch.optim.swa_utils.AveragedModel.html
@@ -4404,7 +4404,7 @@
 <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.swa_utils.</span></span><span class="sig-name descname"><span class="pre">AveragedModel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">avg_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">multi_avg_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_buffers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/swa_utils.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.swa_utils.</span></span><span class="sig-name descname"><span class="pre">AveragedModel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">avg_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">multi_avg_fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_buffers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/swa_utils.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel" title="Permalink to this definition">#</a></dt>
 <dd><p>Implements averaged model for Stochastic Weight Averaging (SWA) and Exponential Moving Average (EMA).</p>
 <p>Stochastic Weight Averaging was proposed in <a class="reference external" href="https://arxiv.org/abs/1803.05407">Averaging Weights Leads to
 Wider Optima and Better Generalization</a> by Pavel Izmailov, Dmitrii
@@ -4493,7 +4493,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.add_module">
-<span class="sig-name descname"><span class="pre">add_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L639"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.add_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L639"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.add_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a child module to the current module.</p>
 <p>The module can be accessed as an attribute using the given name.</p>
 <dl class="field-list simple">
@@ -4509,7 +4509,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.apply">
-<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.apply" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1026"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.apply" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every submodule (as returned by <code class="docutils literal notranslate"><span class="pre">.children()</span></code>) as well as self.</p>
 <p>Typical use includes initializing the parameters of a model
 (see also <a class="reference internal" href="../nn.init.html#nn-init-doc"><span class="std std-ref">torch.nn.init</span></a>).</p>
@@ -4551,7 +4551,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.bfloat16">
-<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.bfloat16" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.bfloat16" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">bfloat16</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4569,7 +4569,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.buffers">
-<span class="sig-name descname"><span class="pre">buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2713"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2713"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module buffers.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4595,7 +4595,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.children">
-<span class="sig-name descname"><span class="pre">children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2767"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.children" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2767"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.children" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over immediate children modules.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -4609,7 +4609,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.compile">
-<span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L3030"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.compile" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">compile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L3030"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.compile" title="Permalink to this definition">#</a></dt>
 <dd><p>Compile this Module’s forward using <a class="reference internal" href="torch.compile.html#torch.compile" title="torch.compile"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.compile()</span></code></a>.</p>
 <p>This Module’s <cite>__call__</cite> method is compiled and all arguments are passed as-is
 to <a class="reference internal" href="torch.compile.html#torch.compile" title="torch.compile"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.compile()</span></code></a>.</p>
@@ -4618,7 +4618,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.cpu">
-<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.cpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1143"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.cpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the CPU.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4636,7 +4636,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.cuda">
-<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.cuda" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.cuda" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the GPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -4661,7 +4661,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.double">
-<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.double" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1179"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.double" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">double</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4679,7 +4679,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.eval">
-<span class="sig-name descname"><span class="pre">eval</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2894"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.eval" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">eval</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2894"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.eval" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module in evaluation mode.</p>
 <p>This has an effect only on certain modules. See the documentation of
 particular modules for details of their behaviors in training/evaluation
@@ -4700,7 +4700,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.extra_repr">
-<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2970"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.extra_repr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extra_repr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2970"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.extra_repr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the extra representation of the module.</p>
 <p>To print customized extra information, you should re-implement
 this method in your own modules. Both single-line and multi-line
@@ -4714,7 +4714,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.float">
-<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.float" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.float" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">float</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4732,13 +4732,13 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.forward">
-<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/swa_utils.py#L244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/swa_utils.py#L244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Forward pass.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.get_buffer">
-<span class="sig-name descname"><span class="pre">get_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.get_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.get_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the buffer given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>See the docstring for <code class="docutils literal notranslate"><span class="pre">get_submodule</span></code> for a more detailed
 explanation of this method’s functionality as well as how to
@@ -4765,7 +4765,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.get_extra_state">
-<span class="sig-name descname"><span class="pre">get_extra_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L889"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.get_extra_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_extra_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L889"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.get_extra_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Return any extra state to include in the module’s state_dict.</p>
 <p>Implement this and a corresponding <a class="reference internal" href="#torch.optim.swa_utils.AveragedModel.set_extra_state" title="torch.optim.swa_utils.AveragedModel.set_extra_state"><code class="xref py py-func docutils literal notranslate"><span class="pre">set_extra_state()</span></code></a> for your module
 if you need to store extra state. This function is called when building the
@@ -4786,7 +4786,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.get_parameter">
-<span class="sig-name descname"><span class="pre">get_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.get_parameter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L817"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.get_parameter" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the parameter given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>See the docstring for <code class="docutils literal notranslate"><span class="pre">get_submodule</span></code> for a more detailed
 explanation of this method’s functionality as well as how to
@@ -4813,7 +4813,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.get_submodule">
-<span class="sig-name descname"><span class="pre">get_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L671"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.get_submodule" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L671"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.get_submodule" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the submodule given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <p>For example, let’s say you have an <code class="docutils literal notranslate"><span class="pre">nn.Module</span></code> <code class="docutils literal notranslate"><span class="pre">A</span></code> that
 looks like this:</p>
@@ -4862,7 +4862,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.half">
-<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.half" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1190"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.half" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all floating point parameters and buffers to <code class="docutils literal notranslate"><span class="pre">half</span></code> datatype.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4880,7 +4880,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.ipu">
-<span class="sig-name descname"><span class="pre">ipu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.ipu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">ipu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1086"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.ipu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the IPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -4905,7 +4905,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assign</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2522"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">assign</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2522"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy parameters and buffers from <a class="reference internal" href="#torch.optim.swa_utils.AveragedModel.state_dict" title="torch.optim.swa_utils.AveragedModel.state_dict"><code class="xref py py-attr docutils literal notranslate"><span class="pre">state_dict</span></code></a> into this module and its descendants.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">strict</span></code> is <code class="docutils literal notranslate"><span class="pre">True</span></code>, then
 the keys of <a class="reference internal" href="#torch.optim.swa_utils.AveragedModel.state_dict" title="torch.optim.swa_utils.AveragedModel.state_dict"><code class="xref py py-attr docutils literal notranslate"><span class="pre">state_dict</span></code></a> must exactly match the keys returned
@@ -4960,7 +4960,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.modules">
-<span class="sig-name descname"><span class="pre">modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2796"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2796"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over all modules in the network.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -4992,7 +4992,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.mtia">
-<span class="sig-name descname"><span class="pre">mtia</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.mtia" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mtia</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1124"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.mtia" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the MTIA.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing the optimizer if the module will
@@ -5017,7 +5017,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.named_buffers">
-<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.named_buffers" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_buffers</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.named_buffers" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5046,7 +5046,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.named_children">
-<span class="sig-name descname"><span class="pre">named_children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.named_children" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_children</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.named_children" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Yields</dt>
@@ -5066,7 +5066,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.named_modules">
-<span class="sig-name descname"><span class="pre">named_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.named_modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_modules</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2823"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.named_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5103,7 +5103,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.named_parameters">
-<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2681"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.named_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">named_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_duplicate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2681"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.named_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5133,7 +5133,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.parameters">
-<span class="sig-name descname"><span class="pre">parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2656"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2656"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an iterator over module parameters.</p>
 <p>This is typically passed to an optimizer.</p>
 <dl class="field-list simple">
@@ -5160,7 +5160,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_backward_hook">
-<span class="sig-name descname"><span class="pre">register_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_backward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1422"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_backward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook on the module.</p>
 <p>This function is deprecated in favor of <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module.register_full_backward_hook" title="torch.nn.Module.register_full_backward_hook"><code class="xref py py-meth docutils literal notranslate"><span class="pre">register_full_backward_hook()</span></code></a> and
 the behavior of this function will change in future versions.</p>
@@ -5177,7 +5177,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_buffer">
-<span class="sig-name descname"><span class="pre">register_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_buffer" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">persistent</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L525"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_buffer" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a buffer to the module.</p>
 <p>This is typically used to register a buffer that should not be
 considered a model parameter. For example, BatchNorm’s <code class="docutils literal notranslate"><span class="pre">running_mean</span></code>
@@ -5209,7 +5209,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_forward_hook">
-<span class="sig-name descname"><span class="pre">register_forward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">always_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_forward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_forward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">always_call</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1678"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_forward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a forward hook on the module.</p>
 <p>The hook will be called every time after <a class="reference internal" href="#torch.optim.swa_utils.AveragedModel.forward" title="torch.optim.swa_utils.AveragedModel.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> has computed an output.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">with_kwargs</span></code> is <code class="docutils literal notranslate"><span class="pre">False</span></code> or not specified, the input contains only
@@ -5260,7 +5260,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_forward_pre_hook">
-<span class="sig-name descname"><span class="pre">register_forward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_forward_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_forward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_forward_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a forward pre-hook on the module.</p>
 <p>The hook will be called every time before <a class="reference internal" href="#torch.optim.swa_utils.AveragedModel.forward" title="torch.optim.swa_utils.AveragedModel.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a> is invoked.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">with_kwargs</span></code> is false or not specified, the input contains only
@@ -5310,7 +5310,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_full_backward_hook">
-<span class="sig-name descname"><span class="pre">register_full_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_full_backward_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_full_backward_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1448"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_full_backward_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward hook on the module.</p>
 <p>The hook will be called every time the gradients with respect to a module are computed, and its firing rules are as follows:</p>
 <blockquote>
@@ -5367,7 +5367,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_full_backward_pre_hook">
-<span class="sig-name descname"><span class="pre">register_full_backward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_full_backward_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_full_backward_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prepend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_full_backward_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward pre-hook on the module.</p>
 <p>The hook will be called every time the gradients for the module are computed.
 The hook should have the following signature:</p>
@@ -5413,7 +5413,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_load_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2312"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2312"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_load_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a post-hook to be run after module’s <code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code> is called.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, incompatible_keys) -&gt; None</p>
@@ -5443,7 +5443,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_load_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_load_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2300"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_load_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a pre-hook to be run before module’s <code class="xref py py-meth docutils literal notranslate"><span class="pre">load_state_dict()</span></code> is called.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -&gt; None  # noqa: B950</p>
@@ -5459,7 +5459,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_module">
-<span class="sig-name descname"><span class="pre">register_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L667"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Alias for <a class="reference internal" href="#torch.optim.swa_utils.AveragedModel.add_module" title="torch.optim.swa_utils.AveragedModel.add_module"><code class="xref py py-func docutils literal notranslate"><span class="pre">add_module()</span></code></a>.</p>
 <dl class="field-list simple">
 </dl>
@@ -5467,7 +5467,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_parameter">
-<span class="sig-name descname"><span class="pre">register_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_parameter" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L589"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_parameter" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a parameter to the module.</p>
 <p>The parameter can be accessed as an attribute using given name.</p>
 <dl class="field-list simple">
@@ -5486,7 +5486,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_state_dict_post_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_post_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_state_dict_post_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a post-hook for the <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module.state_dict" title="torch.nn.Module.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> method.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, state_dict, prefix, local_metadata) -&gt; None</p>
@@ -5497,7 +5497,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.register_state_dict_pre_hook">
-<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_state_dict_pre_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2127"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.register_state_dict_pre_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a pre-hook for the <a class="reference internal" href="torch.nn.Module.html#torch.nn.Module.state_dict" title="torch.nn.Module.state_dict"><code class="xref py py-meth docutils literal notranslate"><span class="pre">state_dict()</span></code></a> method.</p>
 <dl class="simple">
 <dt>It should have the following signature::</dt><dd><p>hook(module, prefix, keep_vars) -&gt; None</p>
@@ -5509,7 +5509,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.requires_grad_">
-<span class="sig-name descname"><span class="pre">requires_grad_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2912"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.requires_grad_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">requires_grad_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2912"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.requires_grad_" title="Permalink to this definition">#</a></dt>
 <dd><p>Change if autograd should record operations on parameters in this module.</p>
 <p>This method sets the parameters’ <code class="xref py py-attr docutils literal notranslate"><span class="pre">requires_grad</span></code> attributes
 in-place.</p>
@@ -5533,7 +5533,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.set_extra_state">
-<span class="sig-name descname"><span class="pre">set_extra_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.set_extra_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_extra_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L910"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.set_extra_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Set extra state contained in the loaded <cite>state_dict</cite>.</p>
 <p>This function is called from <a class="reference internal" href="#torch.optim.swa_utils.AveragedModel.load_state_dict" title="torch.optim.swa_utils.AveragedModel.load_state_dict"><code class="xref py py-func docutils literal notranslate"><span class="pre">load_state_dict()</span></code></a> to handle any extra state
 found within the <cite>state_dict</cite>. Implement this function and a corresponding
@@ -5548,7 +5548,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.set_submodule">
-<span class="sig-name descname"><span class="pre">set_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.set_submodule" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_submodule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">strict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L736"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.set_submodule" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the submodule given by <code class="docutils literal notranslate"><span class="pre">target</span></code> if it exists, otherwise throw an error.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -5606,7 +5606,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.share_memory">
-<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.share_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">share_memory</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.share_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="torch.Tensor.share_memory_.html#torch.Tensor.share_memory_" title="torch.Tensor.share_memory_"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.Tensor.share_memory_()</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5617,7 +5617,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_vars</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_vars</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2191"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary containing references to the whole state of the module.</p>
 <p>Both parameters and persistent buffers (e.g. running averages) are
 included. Keys are corresponding parameter and buffer names.
@@ -5670,27 +5670,27 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.to">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.to" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.to" title="Permalink to this definition">#</a></dt>
 <dd><p>Move and/or cast the parameters and buffers.</p>
 <p>This can be called as</p>
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memory_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.channels_last</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">memory_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.channels_last</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1244"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd></dd></dl>
 
 <p>Its signature is similar to <a class="reference internal" href="torch.Tensor.to.html#torch.Tensor.to" title="torch.Tensor.to"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.Tensor.to()</span></code></a>, but only accepts
@@ -5769,7 +5769,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.to_empty">
-<span class="sig-name descname"><span class="pre">to_empty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.to_empty" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_empty</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1212"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.to_empty" title="Permalink to this definition">#</a></dt>
 <dd><p>Move the parameters and buffers to the specified device without copying storage.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5791,7 +5791,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.train">
-<span class="sig-name descname"><span class="pre">train</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2872"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.train" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">train</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2872"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.train" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module in training mode.</p>
 <p>This has an effect only on certain modules. See the documentation of
 particular modules for details of their behaviors in training/evaluation
@@ -5813,7 +5813,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.type">
-<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dst_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.type" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dst_type</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.type" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts all parameters and buffers to <code class="xref py py-attr docutils literal notranslate"><span class="pre">dst_type</span></code>.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -5834,7 +5834,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.update_parameters">
-<span class="sig-name descname"><span class="pre">update_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/swa_utils.py#L248"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.update_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">update_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/swa_utils.py#L248"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.update_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Update model parameters.</p>
 <dl class="field-list simple">
 </dl>
@@ -5842,7 +5842,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.xpu">
-<span class="sig-name descname"><span class="pre">xpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L1105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.xpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">xpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L1105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.xpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Move all model parameters and buffers to the XPU.</p>
 <p>This also makes associated parameters and buffers different objects. So
 it should be called before constructing optimizer if the module will
@@ -5867,7 +5867,7 @@ <h1>AveragedModel<a class="headerlink" href="#averagedmodel" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.AveragedModel.zero_grad">
-<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/modules/module.py#L2935"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.zero_grad" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">zero_grad</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">set_to_none</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/modules/module.py#L2935"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.AveragedModel.zero_grad" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset gradients of all model parameters.</p>
 <p>See similar function under <a class="reference internal" href="../optim.html#torch.optim.Optimizer" title="torch.optim.Optimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.optim.Optimizer</span></code></a> for more context.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.optim.swa_utils.SWALR.html b/2.9/generated/torch.optim.swa_utils.SWALR.html
index b90dbe9ff50..362461be137 100644
--- a/2.9/generated/torch.optim.swa_utils.SWALR.html
+++ b/2.9/generated/torch.optim.swa_utils.SWALR.html
@@ -4404,7 +4404,7 @@
 <h1>SWALR<a class="headerlink" href="#swalr" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.SWALR">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.swa_utils.</span></span><span class="sig-name descname"><span class="pre">SWALR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swa_lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">anneal_epochs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">anneal_strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cos'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/swa_utils.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.swa_utils.</span></span><span class="sig-name descname"><span class="pre">SWALR</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">optimizer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">swa_lr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">anneal_epochs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">anneal_strategy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cos'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">last_epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/swa_utils.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR" title="Permalink to this definition">#</a></dt>
 <dd><p>Anneals the learning rate in each parameter group to a fixed value.</p>
 <p>This learning rate scheduler is meant to be used with Stochastic Weight
 Averaging (SWA) method (see <cite>torch.optim.swa_utils.AveragedModel</cite>).</p>
@@ -4447,7 +4447,7 @@ <h1>SWALR<a class="headerlink" href="#swalr" title="Permalink to this heading">#
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.SWALR.get_last_lr">
-<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.get_last_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_last_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L168"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.get_last_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Return last computed learning rate by current scheduler.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4458,13 +4458,13 @@ <h1>SWALR<a class="headerlink" href="#swalr" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.SWALR.get_lr">
-<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/swa_utils.py#L459"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.get_lr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_lr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/swa_utils.py#L459"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.get_lr" title="Permalink to this definition">#</a></dt>
 <dd><p>Get learning rate.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.SWALR.load_state_dict">
-<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.load_state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_state_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L159"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.load_state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Load the scheduler’s state.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4476,7 +4476,7 @@ <h1>SWALR<a class="headerlink" href="#swalr" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.SWALR.state_dict">
-<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.state_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">state_dict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.state_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the state of the scheduler as a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">dict</span></code></a>.</p>
 <p>It contains an entry for every variable in self.__dict__ which
 is not the optimizer.</p>
@@ -4489,7 +4489,7 @@ <h1>SWALR<a class="headerlink" href="#swalr" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.SWALR.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">epoch</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/lr_scheduler.py#L176"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.SWALR.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a step.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/generated/torch.pca_lowrank.html b/2.9/generated/torch.pca_lowrank.html
index bf9b2e4fd04..1f2ce047f06 100644
--- a/2.9/generated/torch.pca_lowrank.html
+++ b/2.9/generated/torch.pca_lowrank.html
@@ -4404,7 +4404,7 @@
 <h1>torch.pca_lowrank<a class="headerlink" href="#torch-pca-lowrank" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.pca_lowrank">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">pca_lowrank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">A</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">niter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_lowrank.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.pca_lowrank" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">pca_lowrank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">A</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">niter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_lowrank.py#L184"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.pca_lowrank" title="Permalink to this definition">#</a></dt>
 <dd><p>Performs linear Principal Component Analysis (PCA) on a low-rank
 matrix, batches of such matrices, or sparse matrix.</p>
 <p>This function returns a namedtuple <code class="docutils literal notranslate"><span class="pre">(U,</span> <span class="pre">S,</span> <span class="pre">V)</span></code> which is the
diff --git a/2.9/generated/torch.quasirandom.SobolEngine.html b/2.9/generated/torch.quasirandom.SobolEngine.html
index 319630d32fa..add6ca82752 100644
--- a/2.9/generated/torch.quasirandom.SobolEngine.html
+++ b/2.9/generated/torch.quasirandom.SobolEngine.html
@@ -4404,7 +4404,7 @@
 <h1>SobolEngine<a class="headerlink" href="#sobolengine" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.quasirandom.SobolEngine">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.quasirandom.</span></span><span class="sig-name descname"><span class="pre">SobolEngine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dimension</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scramble</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/quasirandom.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.quasirandom.</span></span><span class="sig-name descname"><span class="pre">SobolEngine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dimension</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scramble</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/quasirandom.py#L7"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine" title="Permalink to this definition">#</a></dt>
 <dd><p>The <a class="reference internal" href="#torch.quasirandom.SobolEngine" title="torch.quasirandom.SobolEngine"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.quasirandom.SobolEngine</span></code></a> is an engine for generating
 (scrambled) Sobol sequences. Sobol sequences are an example of low
 discrepancy quasi-random sequences.</p>
@@ -4446,7 +4446,7 @@ <h1>SobolEngine<a class="headerlink" href="#sobolengine" title="Permalink to thi
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.quasirandom.SobolEngine.draw">
-<span class="sig-name descname"><span class="pre">draw</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/quasirandom.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine.draw" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">draw</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/quasirandom.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine.draw" title="Permalink to this definition">#</a></dt>
 <dd><p>Function to draw a sequence of <code class="xref py py-attr docutils literal notranslate"><span class="pre">n</span></code> points from a Sobol sequence.
 Note that the samples are dependent on the previous samples. The size
 of the result is <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mi>n</mi><mo separator="true">,</mo><mi>d</mi><mi>i</mi><mi>m</mi><mi>e</mi><mi>n</mi><mi>s</mi><mi>i</mi><mi>o</mi><mi>n</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(n, dimension)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord mathnormal">n</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">d</span><span class="mord mathnormal">im</span><span class="mord mathnormal">e</span><span class="mord mathnormal">n</span><span class="mord mathnormal">s</span><span class="mord mathnormal">i</span><span class="mord mathnormal">o</span><span class="mord mathnormal">n</span><span class="mclose">)</span></span></span></span></span>.</p>
@@ -4469,7 +4469,7 @@ <h1>SobolEngine<a class="headerlink" href="#sobolengine" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.quasirandom.SobolEngine.draw_base2">
-<span class="sig-name descname"><span class="pre">draw_base2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/quasirandom.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine.draw_base2" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">draw_base2</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">m</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/quasirandom.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine.draw_base2" title="Permalink to this definition">#</a></dt>
 <dd><p>Function to draw a sequence of <code class="xref py py-attr docutils literal notranslate"><span class="pre">2**m</span></code> points from a Sobol sequence.
 Note that the samples are dependent on the previous samples. The size
 of the result is <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mn>2</mn><mo>∗</mo><mo>∗</mo><mi>m</mi><mo separator="true">,</mo><mi>d</mi><mi>i</mi><mi>m</mi><mi>e</mi><mi>n</mi><mi>s</mi><mi>i</mi><mi>o</mi><mi>n</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(2**m, dimension)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord">2</span><span class="mspace" style="margin-right:0.2222em;"></span><span class="mbin">∗</span><span class="mspace" style="margin-right:0.2222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord">∗</span><span class="mord mathnormal">m</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">d</span><span class="mord mathnormal">im</span><span class="mord mathnormal">e</span><span class="mord mathnormal">n</span><span class="mord mathnormal">s</span><span class="mord mathnormal">i</span><span class="mord mathnormal">o</span><span class="mord mathnormal">n</span><span class="mclose">)</span></span></span></span></span>.</p>
@@ -4491,7 +4491,7 @@ <h1>SobolEngine<a class="headerlink" href="#sobolengine" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.quasirandom.SobolEngine.fast_forward">
-<span class="sig-name descname"><span class="pre">fast_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/quasirandom.py#L169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine.fast_forward" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fast_forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/quasirandom.py#L169"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine.fast_forward" title="Permalink to this definition">#</a></dt>
 <dd><p>Function to fast-forward the state of the <code class="docutils literal notranslate"><span class="pre">SobolEngine</span></code> by
 <code class="xref py py-attr docutils literal notranslate"><span class="pre">n</span></code> steps. This is equivalent to drawing <code class="xref py py-attr docutils literal notranslate"><span class="pre">n</span></code> samples
 without using the samples.</p>
@@ -4504,7 +4504,7 @@ <h1>SobolEngine<a class="headerlink" href="#sobolengine" title="Permalink to thi
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.quasirandom.SobolEngine.reset">
-<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/quasirandom.py#L161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine.reset" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/quasirandom.py#L161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.quasirandom.SobolEngine.reset" title="Permalink to this definition">#</a></dt>
 <dd><p>Function to reset the <code class="docutils literal notranslate"><span class="pre">SobolEngine</span></code> to base state.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.save.html b/2.9/generated/torch.save.html
index 9ad99a8a228..a5f97ef484f 100644
--- a/2.9/generated/torch.save.html
+++ b/2.9/generated/torch.save.html
@@ -4404,7 +4404,7 @@
 <h1>torch.save<a class="headerlink" href="#torch-save" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.save">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">pickle</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_use_new_zipfile_serialization</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L908"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.save" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">pickle</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_use_new_zipfile_serialization</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L908"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.save" title="Permalink to this definition">#</a></dt>
 <dd><p>Saves an object to a disk file.</p>
 <p>See also: <a class="reference internal" href="../notes/serialization.html#saving-loading-tensors"><span class="std std-ref">Saving and loading tensors</span></a></p>
 <p>See <a class="reference internal" href="../notes/serialization.html#layout-control"><span class="std std-ref">Layout Control</span></a> for more advanced tools to manipulate a checkpoint.</p>
diff --git a/2.9/generated/torch.seed.html b/2.9/generated/torch.seed.html
index 43afb9068c3..1dd013dea75 100644
--- a/2.9/generated/torch.seed.html
+++ b/2.9/generated/torch.seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.seed<a class="headerlink" href="#torch-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.seed">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the seed for generating random numbers to a non-deterministic
 random number on all devices. Returns a 64 bit number used to seed the RNG.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.set_default_device.html b/2.9/generated/torch.set_default_device.html
index 3bd5a11a807..8a4644e6a29 100644
--- a/2.9/generated/torch.set_default_device.html
+++ b/2.9/generated/torch.set_default_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.set_default_device<a class="headerlink" href="#torch-set-default-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.set_default_device">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_default_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_default_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_default_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_default_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the default <code class="docutils literal notranslate"><span class="pre">torch.Tensor</span></code> to be allocated on <code class="docutils literal notranslate"><span class="pre">device</span></code>.  This
 does not affect factory function calls which are called with an explicit
 <code class="docutils literal notranslate"><span class="pre">device</span></code> argument.  Factory calls will be performed as if they
diff --git a/2.9/generated/torch.set_default_dtype.html b/2.9/generated/torch.set_default_dtype.html
index f1b18e9f13b..bf4aec7a5bb 100644
--- a/2.9/generated/torch.set_default_dtype.html
+++ b/2.9/generated/torch.set_default_dtype.html
@@ -4404,7 +4404,7 @@
 <h1>torch.set_default_dtype<a class="headerlink" href="#torch-set-default-dtype" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.set_default_dtype">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_default_dtype</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1278"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_default_dtype" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_default_dtype</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1278"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_default_dtype" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the default floating point dtype to <code class="xref py py-attr docutils literal notranslate"><span class="pre">d</span></code>. Supports floating point dtype
 as inputs. Other dtypes will cause torch to raise an exception.</p>
 <p>When PyTorch is initialized its default floating point dtype is torch.float32,
diff --git a/2.9/generated/torch.set_default_tensor_type.html b/2.9/generated/torch.set_default_tensor_type.html
index c79466df002..11e78998f5e 100644
--- a/2.9/generated/torch.set_default_tensor_type.html
+++ b/2.9/generated/torch.set_default_tensor_type.html
@@ -4404,7 +4404,7 @@
 <h1>torch.set_default_tensor_type<a class="headerlink" href="#torch-set-default-tensor-type" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.set_default_tensor_type">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_default_tensor_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1247"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_default_tensor_type" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_default_tensor_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1247"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_default_tensor_type" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p>This function is deprecated as of PyTorch 2.1, please use <a class="reference internal" href="torch.set_default_dtype.html#torch.set_default_dtype" title="torch.set_default_dtype"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.set_default_dtype()</span></code></a> and
diff --git a/2.9/generated/torch.set_deterministic_debug_mode.html b/2.9/generated/torch.set_deterministic_debug_mode.html
index b914f5392bf..a9a45378912 100644
--- a/2.9/generated/torch.set_deterministic_debug_mode.html
+++ b/2.9/generated/torch.set_deterministic_debug_mode.html
@@ -4404,7 +4404,7 @@
 <h1>torch.set_deterministic_debug_mode<a class="headerlink" href="#torch-set-deterministic-debug-mode" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.set_deterministic_debug_mode">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_deterministic_debug_mode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">debug_mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1488"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_deterministic_debug_mode" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_deterministic_debug_mode</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">debug_mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1488"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_deterministic_debug_mode" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the debug mode for deterministic operations.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.set_float32_matmul_precision.html b/2.9/generated/torch.set_float32_matmul_precision.html
index df5922a1847..ed78761d17c 100644
--- a/2.9/generated/torch.set_float32_matmul_precision.html
+++ b/2.9/generated/torch.set_float32_matmul_precision.html
@@ -4404,7 +4404,7 @@
 <h1>torch.set_float32_matmul_precision<a class="headerlink" href="#torch-set-float32-matmul-precision" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.set_float32_matmul_precision">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_float32_matmul_precision</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">precision</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1554"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_float32_matmul_precision" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_float32_matmul_precision</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">precision</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1554"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_float32_matmul_precision" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the internal precision of float32 matrix multiplications.</p>
 <p>Running float32 matrix multiplications in lower precision may significantly increase
 performance, and in some programs the loss of precision has a negligible impact.</p>
diff --git a/2.9/generated/torch.set_printoptions.html b/2.9/generated/torch.set_printoptions.html
index 67916e58f85..80d55e11827 100644
--- a/2.9/generated/torch.set_printoptions.html
+++ b/2.9/generated/torch.set_printoptions.html
@@ -4404,7 +4404,7 @@
 <h1>torch.set_printoptions<a class="headerlink" href="#torch-set-printoptions" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.set_printoptions">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_printoptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">edgeitems</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">linewidth</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sci_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor_str.py#L25"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_printoptions" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_printoptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">edgeitems</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">linewidth</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sci_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor_str.py#L25"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_printoptions" title="Permalink to this definition">#</a></dt>
 <dd><p>Set options for printing. Items shamelessly taken from NumPy</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.set_rng_state.html b/2.9/generated/torch.set_rng_state.html
index c0ba356caf0..fa6b7848dca 100644
--- a/2.9/generated/torch.set_rng_state.html
+++ b/2.9/generated/torch.set_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.set_rng_state<a class="headerlink" href="#torch-set-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.set_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the random number generator state.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.set_warn_always.html b/2.9/generated/torch.set_warn_always.html
index a41abc5c7df..5e5b864207d 100644
--- a/2.9/generated/torch.set_warn_always.html
+++ b/2.9/generated/torch.set_warn_always.html
@@ -4404,7 +4404,7 @@
 <h1>torch.set_warn_always<a class="headerlink" href="#torch-set-warn-always" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.set_warn_always">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_warn_always</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">b</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1620"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_warn_always" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">set_warn_always</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">b</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1620"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.set_warn_always" title="Permalink to this definition">#</a></dt>
 <dd><p>When this flag is False (default) then some PyTorch warnings may only
 appear once per process. This helps avoid excessive warning information.
 Setting it to True causes these warnings to always appear, which may be
diff --git a/2.9/generated/torch.signal.windows.bartlett.html b/2.9/generated/torch.signal.windows.bartlett.html
index 98199a07e50..21dd958aed1 100644
--- a/2.9/generated/torch.signal.windows.bartlett.html
+++ b/2.9/generated/torch.signal.windows.bartlett.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.bartlett<a class="headerlink" href="#torch-signal-windows-bartlett" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.bartlett">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">bartlett</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L588"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.bartlett" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">bartlett</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L588"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.bartlett" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the Bartlett window.</p>
 <p>The Bartlett window is defined as follows:</p>
 <div class="math">
diff --git a/2.9/generated/torch.signal.windows.blackman.html b/2.9/generated/torch.signal.windows.blackman.html
index 9b78355fa25..d69fcd23b7f 100644
--- a/2.9/generated/torch.signal.windows.blackman.html
+++ b/2.9/generated/torch.signal.windows.blackman.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.blackman<a class="headerlink" href="#torch-signal-windows-blackman" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.blackman">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">blackman</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L529"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.blackman" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">blackman</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L529"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.blackman" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the Blackman window.</p>
 <p>The Blackman window is defined as follows:</p>
 <div class="math">
diff --git a/2.9/generated/torch.signal.windows.cosine.html b/2.9/generated/torch.signal.windows.cosine.html
index 3e6c11ac0ed..8db517d5055 100644
--- a/2.9/generated/torch.signal.windows.cosine.html
+++ b/2.9/generated/torch.signal.windows.cosine.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.cosine<a class="headerlink" href="#torch-signal-windows-cosine" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.cosine">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">cosine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L178"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.cosine" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">cosine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L178"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.cosine" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a window with a simple cosine waveform, following the same implementation as SciPy.
 This window is also known as the sine window.</p>
 <p>The cosine window is defined as follows:</p>
diff --git a/2.9/generated/torch.signal.windows.exponential.html b/2.9/generated/torch.signal.windows.exponential.html
index 412f98cf6f6..2598ae1844c 100644
--- a/2.9/generated/torch.signal.windows.exponential.html
+++ b/2.9/generated/torch.signal.windows.exponential.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.exponential<a class="headerlink" href="#torch-signal-windows-exponential" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.exponential">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">exponential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tau</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.exponential" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">exponential</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tau</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L89"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.exponential" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a window with an exponential waveform.
 Also known as Poisson window.</p>
 <p>The exponential window is defined as follows:</p>
diff --git a/2.9/generated/torch.signal.windows.gaussian.html b/2.9/generated/torch.signal.windows.gaussian.html
index 80d77f84520..388b36aeae9 100644
--- a/2.9/generated/torch.signal.windows.gaussian.html
+++ b/2.9/generated/torch.signal.windows.gaussian.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.gaussian<a class="headerlink" href="#torch-signal-windows-gaussian" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.gaussian">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">gaussian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">std</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L254"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.gaussian" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">gaussian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">std</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L254"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.gaussian" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes a window with a gaussian waveform.</p>
 <p>The gaussian window is defined as follows:</p>
 <div class="math">
diff --git a/2.9/generated/torch.signal.windows.general_cosine.html b/2.9/generated/torch.signal.windows.general_cosine.html
index 08007fd0c60..da6643594c1 100644
--- a/2.9/generated/torch.signal.windows.general_cosine.html
+++ b/2.9/generated/torch.signal.windows.general_cosine.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.general_cosine<a class="headerlink" href="#torch-signal-windows-general-cosine" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.general_cosine">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">general_cosine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L664"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.general_cosine" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">general_cosine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L664"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.general_cosine" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the general cosine window.</p>
 <p>The general cosine window is defined as follows:</p>
 <div class="math">
diff --git a/2.9/generated/torch.signal.windows.general_hamming.html b/2.9/generated/torch.signal.windows.general_hamming.html
index df0085c8dcc..00976db665e 100644
--- a/2.9/generated/torch.signal.windows.general_hamming.html
+++ b/2.9/generated/torch.signal.windows.general_hamming.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.general_hamming<a class="headerlink" href="#torch-signal-windows-general-hamming" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.general_hamming">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">general_hamming</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.54</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L757"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.general_hamming" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">general_hamming</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alpha</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.54</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L757"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.general_hamming" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the general Hamming window.</p>
 <p>The general Hamming window is defined as follows:</p>
 <div class="math">
diff --git a/2.9/generated/torch.signal.windows.hamming.html b/2.9/generated/torch.signal.windows.hamming.html
index 0b2affed45c..6715b8b769e 100644
--- a/2.9/generated/torch.signal.windows.hamming.html
+++ b/2.9/generated/torch.signal.windows.hamming.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.hamming<a class="headerlink" href="#torch-signal-windows-hamming" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.hamming">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">hamming</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.hamming" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">hamming</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L419"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.hamming" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the Hamming window.</p>
 <p>The Hamming window is defined as follows:</p>
 <div class="math">
diff --git a/2.9/generated/torch.signal.windows.hann.html b/2.9/generated/torch.signal.windows.hann.html
index 7186a108d46..5dd8a9b1f62 100644
--- a/2.9/generated/torch.signal.windows.hann.html
+++ b/2.9/generated/torch.signal.windows.hann.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.hann<a class="headerlink" href="#torch-signal-windows-hann" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.hann">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">hann</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L474"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.hann" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">hann</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L474"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.hann" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the Hann window.</p>
 <p>The Hann window is defined as follows:</p>
 <div class="math">
diff --git a/2.9/generated/torch.signal.windows.kaiser.html b/2.9/generated/torch.signal.windows.kaiser.html
index 93380e6a330..acad40a5c9d 100644
--- a/2.9/generated/torch.signal.windows.kaiser.html
+++ b/2.9/generated/torch.signal.windows.kaiser.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.kaiser<a class="headerlink" href="#torch-signal-windows-kaiser" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.kaiser">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">kaiser</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">12.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.kaiser" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">kaiser</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">beta</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">12.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.kaiser" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the Kaiser window.</p>
 <p>The Kaiser window is defined as follows:</p>
 <div class="math">
diff --git a/2.9/generated/torch.signal.windows.nuttall.html b/2.9/generated/torch.signal.windows.nuttall.html
index 7468b4e261a..53733fa4472 100644
--- a/2.9/generated/torch.signal.windows.nuttall.html
+++ b/2.9/generated/torch.signal.windows.nuttall.html
@@ -4404,7 +4404,7 @@
 <h1>torch.signal.windows.nuttall<a class="headerlink" href="#torch-signal-windows-nuttall" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.signal.windows.nuttall">
-<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">nuttall</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/signal/windows/windows.py#L813"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.nuttall" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.signal.windows.</span></span><span class="sig-name descname"><span class="pre">nuttall</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">M</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sym</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/signal/windows/windows.py#L813"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.signal.windows.nuttall" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the minimum 4-term Blackman-Harris window according to Nuttall.</p>
 <div class="math">
 <span class="katex-display"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><semantics><mrow><msub><mi>w</mi><mi>n</mi></msub><mo>=</mo><mn>1</mn><mo>−</mo><mn>0.36358</mn><mi>cos</mi><mo>⁡</mo><mrow><mo stretchy="false">(</mo><msub><mi>z</mi><mi>n</mi></msub><mo stretchy="false">)</mo></mrow><mo>+</mo><mn>0.48917</mn><mi>cos</mi><mo>⁡</mo><mrow><mo stretchy="false">(</mo><mn>2</mn><msub><mi>z</mi><mi>n</mi></msub><mo stretchy="false">)</mo></mrow><mo>−</mo><mn>0.13659</mn><mi>cos</mi><mo>⁡</mo><mrow><mo stretchy="false">(</mo><mn>3</mn><msub><mi>z</mi><mi>n</mi></msub><mo stretchy="false">)</mo></mrow><mo>+</mo><mn>0.01064</mn><mi>cos</mi><mo>⁡</mo><mrow><mo stretchy="false">(</mo><mn>4</mn><msub><mi>z</mi><mi>n</mi></msub><mo stretchy="false">)</mo></mrow></mrow><annotation encoding="application/x-tex">w_n = 1 - 0.36358 \cos{(z_n)} + 0.48917 \cos{(2z_n)} - 0.13659 \cos{(3z_n)} + 0.01064 \cos{(4z_n)}
diff --git a/2.9/generated/torch.sparse.as_sparse_gradcheck.html b/2.9/generated/torch.sparse.as_sparse_gradcheck.html
index 1ca1d3a17b0..e043b4abc17 100644
--- a/2.9/generated/torch.sparse.as_sparse_gradcheck.html
+++ b/2.9/generated/torch.sparse.as_sparse_gradcheck.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sparse.as_sparse_gradcheck<a class="headerlink" href="#torch-sparse-as-sparse-gradcheck" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sparse.as_sparse_gradcheck">
-<span class="sig-prename descclassname"><span class="pre">torch.sparse.</span></span><span class="sig-name descname"><span class="pre">as_sparse_gradcheck</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">gradcheck</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/sparse/__init__.py#L549"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.as_sparse_gradcheck" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.sparse.</span></span><span class="sig-name descname"><span class="pre">as_sparse_gradcheck</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">gradcheck</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/sparse/__init__.py#L549"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.as_sparse_gradcheck" title="Permalink to this definition">#</a></dt>
 <dd><p>Decorate function, to extend gradcheck for sparse tensors.</p>
 <p>Decorator for torch.autograd.gradcheck or its functools.partial
 variants that extends the gradcheck function with support to input
diff --git a/2.9/generated/torch.sparse.check_sparse_tensor_invariants.html b/2.9/generated/torch.sparse.check_sparse_tensor_invariants.html
index 931cab66a37..a1689faddfb 100644
--- a/2.9/generated/torch.sparse.check_sparse_tensor_invariants.html
+++ b/2.9/generated/torch.sparse.check_sparse_tensor_invariants.html
@@ -4404,7 +4404,7 @@
 <h1>check_sparse_tensor_invariants<a class="headerlink" href="#check-sparse-tensor-invariants" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.sparse.check_sparse_tensor_invariants">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.sparse.</span></span><span class="sig-name descname"><span class="pre">check_sparse_tensor_invariants</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/sparse/__init__.py#L437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.check_sparse_tensor_invariants" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.sparse.</span></span><span class="sig-name descname"><span class="pre">check_sparse_tensor_invariants</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/sparse/__init__.py#L437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.check_sparse_tensor_invariants" title="Permalink to this definition">#</a></dt>
 <dd><p>A tool to control checking sparse tensor invariants.</p>
 <p>The following options exists to manage sparsr tensor invariants
 checking in sparse tensor construction:</p>
@@ -4447,14 +4447,14 @@ <h1>check_sparse_tensor_invariants<a class="headerlink" href="#check-sparse-tens
 </ol>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.sparse.check_sparse_tensor_invariants.disable">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">disable</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/sparse/__init__.py#L513"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.check_sparse_tensor_invariants.disable" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">disable</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/sparse/__init__.py#L513"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.check_sparse_tensor_invariants.disable" title="Permalink to this definition">#</a></dt>
 <dd><p>Disable sparse tensor invariants checking in sparse tensor constructors.</p>
 <p>See <a class="reference internal" href="#torch.sparse.check_sparse_tensor_invariants.enable" title="torch.sparse.check_sparse_tensor_invariants.enable"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.sparse.check_sparse_tensor_invariants.enable()</span></code></a> for more information.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.sparse.check_sparse_tensor_invariants.enable">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">enable</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/sparse/__init__.py#L493"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.check_sparse_tensor_invariants.enable" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">enable</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/sparse/__init__.py#L493"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.check_sparse_tensor_invariants.enable" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable sparse tensor invariants checking in sparse tensor constructors.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4473,7 +4473,7 @@ <h1>check_sparse_tensor_invariants<a class="headerlink" href="#check-sparse-tens
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.sparse.check_sparse_tensor_invariants.is_enabled">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">is_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/sparse/__init__.py#L481"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.check_sparse_tensor_invariants.is_enabled" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">is_enabled</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/sparse/__init__.py#L481"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.check_sparse_tensor_invariants.is_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Return True if the sparse tensor invariants checking is enabled.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.sparse.sum.html b/2.9/generated/torch.sparse.sum.html
index 4f7d1297330..78740f4c973 100644
--- a/2.9/generated/torch.sparse.sum.html
+++ b/2.9/generated/torch.sparse.sum.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sparse.sum<a class="headerlink" href="#torch-sparse-sum" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sparse.sum">
-<span class="sig-prename descclassname"><span class="pre">torch.sparse.</span></span><span class="sig-name descname"><span class="pre">sum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/sparse/__init__.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.sum" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.sparse.</span></span><span class="sig-name descname"><span class="pre">sum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/sparse/__init__.py#L201"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sparse.sum" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the sum of each row of the given sparse tensor.</p>
 <p>Returns the sum of each row of the sparse tensor <code class="xref py py-attr docutils literal notranslate"><span class="pre">input</span></code> in the given
 dimensions <code class="xref py py-attr docutils literal notranslate"><span class="pre">dim</span></code>. If <code class="xref py py-attr docutils literal notranslate"><span class="pre">dim</span></code> is a list of dimensions,
diff --git a/2.9/generated/torch.split.html b/2.9/generated/torch.split.html
index 819bdec6232..8b10763e59b 100644
--- a/2.9/generated/torch.split.html
+++ b/2.9/generated/torch.split.html
@@ -4404,7 +4404,7 @@
 <h1>torch.split<a class="headerlink" href="#torch-split" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.split">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_size_or_sections</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.split" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_size_or_sections</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.split" title="Permalink to this definition">#</a></dt>
 <dd><p>Splits the tensor into chunks. Each chunk is a view of the original tensor.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">split_size_or_sections</span></code> is an integer type, then <a class="reference internal" href="torch.tensor.html#torch.tensor" title="torch.tensor"><code class="xref py py-attr docutils literal notranslate"><span class="pre">tensor</span></code></a> will
 be split into equally sized chunks (if possible). Last chunk will be smaller if
diff --git a/2.9/generated/torch.stft.html b/2.9/generated/torch.stft.html
index 2c8e74c2bf3..a0e5d3fc21a 100644
--- a/2.9/generated/torch.stft.html
+++ b/2.9/generated/torch.stft.html
@@ -4404,7 +4404,7 @@
 <h1>torch.stft<a class="headerlink" href="#torch-stft" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.stft">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">stft</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_fft</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">win_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reflect'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onesided</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_to_window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.stft" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">stft</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n_fft</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hop_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">win_length</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">center</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pad_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'reflect'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalized</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">onesided</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_complex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">align_to_window</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L508"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.stft" title="Permalink to this definition">#</a></dt>
 <dd><p>Short-time Fourier transform (STFT).</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.svd_lowrank.html b/2.9/generated/torch.svd_lowrank.html
index 1702efa47ff..1eb1f1722be 100644
--- a/2.9/generated/torch.svd_lowrank.html
+++ b/2.9/generated/torch.svd_lowrank.html
@@ -4404,7 +4404,7 @@
 <h1>torch.svd_lowrank<a class="headerlink" href="#torch-svd-lowrank" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.svd_lowrank">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">svd_lowrank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">A</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">niter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">M</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_lowrank.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.svd_lowrank" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">svd_lowrank</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">A</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">6</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">niter</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">M</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_lowrank.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.svd_lowrank" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the singular value decomposition <code class="docutils literal notranslate"><span class="pre">(U,</span> <span class="pre">S,</span> <span class="pre">V)</span></code> of a matrix,
 batches of matrices, or a sparse matrix <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>A</mi></mrow><annotation encoding="application/x-tex">A</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal">A</span></span></span></span></span> such that
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>A</mi><mo>≈</mo><mi>U</mi><mi mathvariant="normal">diag</mi><mo>⁡</mo><mo stretchy="false">(</mo><mi>S</mi><mo stretchy="false">)</mo><msup><mi>V</mi><mtext>H</mtext></msup></mrow><annotation encoding="application/x-tex">A \approx U \operatorname{diag}(S) V^{\text{H}}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal">A</span><span class="mspace" style="margin-right:0.2778em;"></span><span class="mrel">≈</span><span class="mspace" style="margin-right:0.2778em;"></span></span><span class="base"><span class="strut" style="height:1.0913em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">U</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mop"><span class="mord mathrm" style="margin-right:0.01389em;">diag</span></span><span class="mopen">(</span><span class="mord mathnormal" style="margin-right:0.05764em;">S</span><span class="mclose">)</span><span class="mord"><span class="mord mathnormal" style="margin-right:0.22222em;">V</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8413em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord text mtight"><span class="mord mtight">H</span></span></span></span></span></span></span></span></span></span></span></span></span></span>. In case <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>M</mi></mrow><annotation encoding="application/x-tex">M</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6833em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">M</span></span></span></span></span> is given, then
diff --git a/2.9/generated/torch.sym_float.html b/2.9/generated/torch.sym_float.html
index e8fe4a4eb5e..8cb28c42915 100644
--- a/2.9/generated/torch.sym_float.html
+++ b/2.9/generated/torch.sym_float.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sym_float<a class="headerlink" href="#torch-sym-float" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sym_float">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L831"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_float" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_float</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L831"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_float" title="Permalink to this definition">#</a></dt>
 <dd><p>SymInt-aware utility for float casting.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.sym_fresh_size.html b/2.9/generated/torch.sym_fresh_size.html
index 36a46b7ce9d..74a225d3885 100644
--- a/2.9/generated/torch.sym_fresh_size.html
+++ b/2.9/generated/torch.sym_fresh_size.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sym_fresh_size<a class="headerlink" href="#torch-sym-fresh-size" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sym_fresh_size">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_fresh_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L999"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_fresh_size" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_fresh_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">expr</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L999"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_fresh_size" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
diff --git a/2.9/generated/torch.sym_int.html b/2.9/generated/torch.sym_int.html
index 900065b199d..b9b046b4447 100644
--- a/2.9/generated/torch.sym_int.html
+++ b/2.9/generated/torch.sym_int.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sym_int<a class="headerlink" href="#torch-sym-int" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sym_int">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_int</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L846"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_int" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_int</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L846"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_int" title="Permalink to this definition">#</a></dt>
 <dd><p>SymInt-aware utility for int casting.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.sym_ite.html b/2.9/generated/torch.sym_ite.html
index 7ee6024f88f..95c0ef4ffd2 100644
--- a/2.9/generated/torch.sym_ite.html
+++ b/2.9/generated/torch.sym_ite.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sym_ite<a class="headerlink" href="#torch-sym-ite" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sym_ite">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_ite</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L988"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_ite" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_ite</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L988"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_ite" title="Permalink to this definition">#</a></dt>
 <dd><p>SymInt-aware utility for ternary operator (<code class="docutils literal notranslate"><span class="pre">t</span> <span class="pre">if</span> <span class="pre">b</span> <span class="pre">else</span> <span class="pre">f</span></code>.)</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.sym_max.html b/2.9/generated/torch.sym_max.html
index 75628ca171c..d1120070dc8 100644
--- a/2.9/generated/torch.sym_max.html
+++ b/2.9/generated/torch.sym_max.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sym_max<a class="headerlink" href="#torch-sym-max" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sym_max">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_max</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L861"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_max" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_max</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L861"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_max" title="Permalink to this definition">#</a></dt>
 <dd><p>SymInt-aware utility for max which avoids branching on a &lt; b.
 Unlike builtins.max(), this only works for int/float, and it always
 promotes to float if any argument is float (unlike builtins.max, which
diff --git a/2.9/generated/torch.sym_min.html b/2.9/generated/torch.sym_min.html
index 82e7ad1e2fc..597b758028c 100644
--- a/2.9/generated/torch.sym_min.html
+++ b/2.9/generated/torch.sym_min.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sym_min<a class="headerlink" href="#torch-sym-min" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sym_min">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_min</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L906"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_min" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_min</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L906"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_min" title="Permalink to this definition">#</a></dt>
 <dd><p>SymInt-aware utility for min().</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.sym_not.html b/2.9/generated/torch.sym_not.html
index 0bb545211c9..0504ac39c1c 100644
--- a/2.9/generated/torch.sym_not.html
+++ b/2.9/generated/torch.sym_not.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sym_not<a class="headerlink" href="#torch-sym-not" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sym_not">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_not</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_not" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_not</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L814"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_not" title="Permalink to this definition">#</a></dt>
 <dd><p>SymInt-aware utility for logical negation.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.sym_sum.html b/2.9/generated/torch.sym_sum.html
index 25e7dc8db15..48c2e179d48 100644
--- a/2.9/generated/torch.sym_sum.html
+++ b/2.9/generated/torch.sym_sum.html
@@ -4404,7 +4404,7 @@
 <h1>torch.sym_sum<a class="headerlink" href="#torch-sym-sum" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.sym_sum">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_sum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L925"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_sum" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">sym_sum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">args</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L925"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.sym_sum" title="Permalink to this definition">#</a></dt>
 <dd><p>N-ary add which is faster to compute for long lists than iterated binary
 addition.  Only does something special for integers.</p>
 </dd></dl>
diff --git a/2.9/generated/torch.tensordot.html b/2.9/generated/torch.tensordot.html
index 8d4d826b266..c887f0f0992 100644
--- a/2.9/generated/torch.tensordot.html
+++ b/2.9/generated/torch.tensordot.html
@@ -4404,7 +4404,7 @@
 <h1>torch.tensordot<a class="headerlink" href="#torch-tensordot" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.tensordot">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">tensordot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.tensordot" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">tensordot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">a</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1236"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.tensordot" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a contraction of a and b over multiple dimensions.</p>
 <p><a class="reference internal" href="#torch.tensordot" title="torch.tensordot"><code class="xref py py-attr docutils literal notranslate"><span class="pre">tensordot</span></code></a> implements a generalized matrix product.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.unique.html b/2.9/generated/torch.unique.html
index 8c53871f727..fc05d186219 100644
--- a/2.9/generated/torch.unique.html
+++ b/2.9/generated/torch.unique.html
@@ -4404,7 +4404,7 @@
 <h1>torch.unique<a class="headerlink" href="#torch-unique" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.unique">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">unique</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_inverse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_counts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.unique" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">unique</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sorted</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_inverse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_counts</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.14)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="../tensors.html#torch.Tensor" title="torch.Tensor"><span class="pre">Tensor</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.unique" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the unique elements of the input tensor.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.unique_consecutive.html b/2.9/generated/torch.unique_consecutive.html
index 6f6bb035b10..0979b85158d 100644
--- a/2.9/generated/torch.unique_consecutive.html
+++ b/2.9/generated/torch.unique_consecutive.html
@@ -4404,7 +4404,7 @@
 <h1>torch.unique_consecutive<a class="headerlink" href="#torch-unique-consecutive" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.unique_consecutive">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">unique_consecutive</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.unique_consecutive" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">unique_consecutive</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_jit_internal.py#L617"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.unique_consecutive" title="Permalink to this definition">#</a></dt>
 <dd><p>Eliminates all but the first element from every consecutive group of equivalent elements.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/generated/torch.unravel_index.html b/2.9/generated/torch.unravel_index.html
index e95c5974179..469000b60e9 100644
--- a/2.9/generated/torch.unravel_index.html
+++ b/2.9/generated/torch.unravel_index.html
@@ -4404,7 +4404,7 @@
 <h1>torch.unravel_index<a class="headerlink" href="#torch-unravel-index" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.unravel_index">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">unravel_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/functional.py#L1881"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.unravel_index" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">unravel_index</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/functional.py#L1881"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.unravel_index" title="Permalink to this definition">#</a></dt>
 <dd><p>Converts a tensor of flat indices into a tuple of coordinate tensors that
 index into an arbitrary tensor of the specified shape.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.use_deterministic_algorithms.html b/2.9/generated/torch.use_deterministic_algorithms.html
index e1b7c8f4629..e16f7832e35 100644
--- a/2.9/generated/torch.use_deterministic_algorithms.html
+++ b/2.9/generated/torch.use_deterministic_algorithms.html
@@ -4404,7 +4404,7 @@
 <h1>torch.use_deterministic_algorithms<a class="headerlink" href="#torch-use-deterministic-algorithms" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.use_deterministic_algorithms">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">use_deterministic_algorithms</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">warn_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1331"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.use_deterministic_algorithms" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">use_deterministic_algorithms</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mode</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">warn_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1331"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.use_deterministic_algorithms" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets whether PyTorch operations must use “deterministic”
 algorithms. That is, algorithms which, given the same input, and when
 run on the same software and hardware, always produce the same output.
diff --git a/2.9/generated/torch.utils.generate_methods_for_privateuse1_backend.html b/2.9/generated/torch.utils.generate_methods_for_privateuse1_backend.html
index 7de3798f02a..ff570145776 100644
--- a/2.9/generated/torch.utils.generate_methods_for_privateuse1_backend.html
+++ b/2.9/generated/torch.utils.generate_methods_for_privateuse1_backend.html
@@ -4404,7 +4404,7 @@
 <h1>torch.utils.generate_methods_for_privateuse1_backend<a class="headerlink" href="#torch-utils-generate-methods-for-privateuse1-backend" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.generate_methods_for_privateuse1_backend">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">generate_methods_for_privateuse1_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">for_tensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_packed_sequence</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unsupported_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/backend_registration.py#L345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.generate_methods_for_privateuse1_backend" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">generate_methods_for_privateuse1_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">for_tensor</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_module</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_packed_sequence</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">for_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unsupported_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/backend_registration.py#L345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.generate_methods_for_privateuse1_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Automatically generate attributes and methods for the custom backend after rename privateuse1 backend.</p>
 <p>In the default scenario, storage-related methods will not be generated automatically.</p>
 <p>When you implement kernels for various torch operations, and register them to the PrivateUse1 dispatch key.
diff --git a/2.9/generated/torch.utils.get_cpp_backtrace.html b/2.9/generated/torch.utils.get_cpp_backtrace.html
index 0227a946a13..c26da595adf 100644
--- a/2.9/generated/torch.utils.get_cpp_backtrace.html
+++ b/2.9/generated/torch.utils.get_cpp_backtrace.html
@@ -4404,7 +4404,7 @@
 <h1>torch.utils.get_cpp_backtrace<a class="headerlink" href="#torch-utils-get-cpp-backtrace" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.get_cpp_backtrace">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">get_cpp_backtrace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">frames_to_skip</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximum_number_of_frames</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">64</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/cpp_backtrace.py#L4"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.get_cpp_backtrace" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">get_cpp_backtrace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">frames_to_skip</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">maximum_number_of_frames</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">64</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/cpp_backtrace.py#L4"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.get_cpp_backtrace" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a string containing the C++ stack trace of the current thread.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.utils.rename_privateuse1_backend.html b/2.9/generated/torch.utils.rename_privateuse1_backend.html
index 766518e9cab..c58fa5d04bb 100644
--- a/2.9/generated/torch.utils.rename_privateuse1_backend.html
+++ b/2.9/generated/torch.utils.rename_privateuse1_backend.html
@@ -4404,7 +4404,7 @@
 <h1>torch.utils.rename_privateuse1_backend<a class="headerlink" href="#torch-utils-rename-privateuse1-backend" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.rename_privateuse1_backend">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">rename_privateuse1_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/backend_registration.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.rename_privateuse1_backend" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">rename_privateuse1_backend</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">backend_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/backend_registration.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.rename_privateuse1_backend" title="Permalink to this definition">#</a></dt>
 <dd><p>Rename the privateuse1 backend device to make it more convenient to use as a device name within PyTorch APIs.</p>
 <p>The steps are:</p>
 <ol class="arabic simple">
diff --git a/2.9/generated/torch.utils.set_module.html b/2.9/generated/torch.utils.set_module.html
index 92f79e2a110..c7bee044c3b 100644
--- a/2.9/generated/torch.utils.set_module.html
+++ b/2.9/generated/torch.utils.set_module.html
@@ -4404,7 +4404,7 @@
 <h1>torch.utils.set_module<a class="headerlink" href="#torch-utils-set-module" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.set_module">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">set_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/__init__.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.set_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">set_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/__init__.py#L23"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.set_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the module attribute on a python object for a given object for nicer printing</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.utils.swap_tensors.html b/2.9/generated/torch.utils.swap_tensors.html
index 5d462e23f12..2dce16ecc1e 100644
--- a/2.9/generated/torch.utils.swap_tensors.html
+++ b/2.9/generated/torch.utils.swap_tensors.html
@@ -4404,7 +4404,7 @@
 <h1>torch.utils.swap_tensors<a class="headerlink" href="#torch-utils-swap-tensors" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.swap_tensors">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">swap_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/__init__.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.swap_tensors" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.</span></span><span class="sig-name descname"><span class="pre">swap_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">t1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">t2</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/__init__.py#L35"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.swap_tensors" title="Permalink to this definition">#</a></dt>
 <dd><p>This function swaps the content of the two Tensor objects.
 At a high level, this will make t1 have the content of t2 while preserving
 its identity.</p>
diff --git a/2.9/generated/torch.vmap.html b/2.9/generated/torch.vmap.html
index 82ed04ba6a7..195ddb971f6 100644
--- a/2.9/generated/torch.vmap.html
+++ b/2.9/generated/torch.vmap.html
@@ -4404,7 +4404,7 @@
 <h1>torch.vmap<a class="headerlink" href="#torch-vmap" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.vmap">
-<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">randomness</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'error'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_functorch/apis.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.vmap" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">in_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_dims</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">randomness</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'error'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">chunk_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_functorch/apis.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.vmap" title="Permalink to this definition">#</a></dt>
 <dd><p>vmap is the vectorizing map; <code class="docutils literal notranslate"><span class="pre">vmap(func)</span></code> returns a new function that
 maps <code class="docutils literal notranslate"><span class="pre">func</span></code> over some dimension of the inputs. Semantically, vmap
 pushes the map into PyTorch operations called by <code class="docutils literal notranslate"><span class="pre">func</span></code>, effectively
diff --git a/2.9/generated/torch.xpu.Event.html b/2.9/generated/torch.xpu.Event.html
index c68e3521cce..e6487b7af2b 100644
--- a/2.9/generated/torch.xpu.Event.html
+++ b/2.9/generated/torch.xpu.Event.html
@@ -4404,7 +4404,7 @@
 <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.xpu.Event">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">Event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable_timing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">Event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable_timing</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L103"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around a XPU event.</p>
 <p>XPU events are synchronization markers that can be used to monitor the
 device’s progress, and to synchronize XPU streams.</p>
@@ -4419,7 +4419,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Event.elapsed_time">
-<span class="sig-name descname"><span class="pre">elapsed_time</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">end_event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.elapsed_time" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">elapsed_time</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">end_event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.elapsed_time" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the time elapsed.</p>
 <p>Time reported in milliseconds after the event was recorded and
 before the end_event was recorded.</p>
@@ -4427,7 +4427,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Event.query">
-<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.query" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L140"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.query" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if all work currently captured by event has completed.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4442,7 +4442,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Event.record">
-<span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.record" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L121"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.record" title="Permalink to this definition">#</a></dt>
 <dd><p>Record the event in a given stream.</p>
 <p>Uses <code class="docutils literal notranslate"><span class="pre">torch.xpu.current_stream()</span></code> if no stream is specified. The
 stream’s device must match the event’s device.</p>
@@ -4452,7 +4452,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Event.synchronize">
-<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait for the event to complete.</p>
 <p>Waits until the completion of all work currently captured in this event.
 This prevents the CPU thread from proceeding until the event completes.</p>
@@ -4462,7 +4462,7 @@ <h1>Event<a class="headerlink" href="#event" title="Permalink to this heading">#
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Event.wait">
-<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.wait" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L131"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Event.wait" title="Permalink to this definition">#</a></dt>
 <dd><p>Make all future work submitted to the given stream wait for this event.</p>
 <p>Use <code class="docutils literal notranslate"><span class="pre">torch.xpu.current_stream()</span></code> if no stream is specified.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.xpu.Stream.html b/2.9/generated/torch.xpu.Stream.html
index fd3551111d0..8db0ca06a8b 100644
--- a/2.9/generated/torch.xpu.Stream.html
+++ b/2.9/generated/torch.xpu.Stream.html
@@ -4404,7 +4404,7 @@
 <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.xpu.Stream">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">Stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">priority</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">Stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">priority</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L14"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrapper around a XPU stream.</p>
 <p>A XPU stream is a linear sequence of execution that belongs to a specific
 device, independent from other streams. It supports with statement as a
@@ -4426,7 +4426,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Stream.query">
-<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.query" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">query</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L75"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.query" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if all the work submitted has been completed.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4440,7 +4440,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Stream.record_event">
-<span class="sig-name descname"><span class="pre">record_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.record_event" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">record_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.record_event" title="Permalink to this definition">#</a></dt>
 <dd><p>Record an event.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4455,7 +4455,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Stream.synchronize">
-<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L83"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L83"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait for all the kernels in this stream to complete.</p>
 <dl class="field-list simple">
 </dl>
@@ -4463,7 +4463,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Stream.wait_event">
-<span class="sig-name descname"><span class="pre">wait_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.wait_event" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait_event</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">event</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.wait_event" title="Permalink to this definition">#</a></dt>
 <dd><p>Make all future work submitted to the stream wait for an event.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4474,7 +4474,7 @@ <h1>Stream<a class="headerlink" href="#stream" title="Permalink to this heading"
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.xpu.Stream.wait_stream">
-<span class="sig-name descname"><span class="pre">wait_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/streams.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.wait_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">wait_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/streams.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.Stream.wait_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Synchronize with another stream.</p>
 <p>All future work submitted to this stream will wait until all kernels
 submitted to a given stream at the time of call complete.</p>
diff --git a/2.9/generated/torch.xpu.StreamContext.html b/2.9/generated/torch.xpu.StreamContext.html
index ec453509868..928c1481033 100644
--- a/2.9/generated/torch.xpu.StreamContext.html
+++ b/2.9/generated/torch.xpu.StreamContext.html
@@ -4404,7 +4404,7 @@
 <h1>StreamContext<a class="headerlink" href="#streamcontext" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.xpu.StreamContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">StreamContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.StreamContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">StreamContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.StreamContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that selects a given stream.</p>
 <p>All XPU kernels queued within its context will be enqueued on a selected
 stream.</p>
diff --git a/2.9/generated/torch.xpu.current_device.html b/2.9/generated/torch.xpu.current_device.html
index 6f08990ac17..0c44ee88594 100644
--- a/2.9/generated/torch.xpu.current_device.html
+++ b/2.9/generated/torch.xpu.current_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.current_device<a class="headerlink" href="#torch-xpu-current-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.current_device">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">current_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L264"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.current_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">current_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L264"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.current_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the index of a currently selected device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.xpu.current_stream.html b/2.9/generated/torch.xpu.current_stream.html
index 61ef847d779..9ebf6284f5e 100644
--- a/2.9/generated/torch.xpu.current_stream.html
+++ b/2.9/generated/torch.xpu.current_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.current_stream<a class="headerlink" href="#torch-xpu-current-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.current_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L368"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.current_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">current_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L368"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.current_stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the currently selected <a class="reference internal" href="torch.xpu.Stream.html#torch.xpu.Stream" title="torch.xpu.Stream"><code class="xref py py-class docutils literal notranslate"><span class="pre">Stream</span></code></a> for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.device.html b/2.9/generated/torch.xpu.device.html
index 51dd20e229f..81fc7b64649 100644
--- a/2.9/generated/torch.xpu.device.html
+++ b/2.9/generated/torch.xpu.device.html
@@ -4404,7 +4404,7 @@
 <h1>device<a class="headerlink" href="#device" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.xpu.device">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.device" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.device" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that changes the selected device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.device_count.html b/2.9/generated/torch.xpu.device_count.html
index 199b7574a73..0f6bf09c61e 100644
--- a/2.9/generated/torch.xpu.device_count.html
+++ b/2.9/generated/torch.xpu.device_count.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.device_count<a class="headerlink" href="#torch-xpu-device-count" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.device_count">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.device_count" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">device_count</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.device_count" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the number of XPU device available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.xpu.device_of.html b/2.9/generated/torch.xpu.device_of.html
index 72bff2451f2..50d8e1b4c4e 100644
--- a/2.9/generated/torch.xpu.device_of.html
+++ b/2.9/generated/torch.xpu.device_of.html
@@ -4404,7 +4404,7 @@
 <h1>device_of<a class="headerlink" href="#device-of" title="Permalink to this heading">#</a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.xpu.device_of">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">device_of</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.device_of" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">device_of</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.device_of" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that changes the current device to that of given object.</p>
 <p>You can use both tensors and storages as arguments. If a given object is
 not allocated on a XPU, this is a no-op.</p>
diff --git a/2.9/generated/torch.xpu.get_arch_list.html b/2.9/generated/torch.xpu.get_arch_list.html
index 7dbcb6dbf3c..e16a37d7d7e 100644
--- a/2.9/generated/torch.xpu.get_arch_list.html
+++ b/2.9/generated/torch.xpu.get_arch_list.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.get_arch_list<a class="headerlink" href="#torch-xpu-get-arch-list" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.get_arch_list">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_arch_list</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_arch_list" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_arch_list</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L426"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_arch_list" title="Permalink to this definition">#</a></dt>
 <dd><p>Return list XPU architectures this library was compiled for.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.xpu.get_device_capability.html b/2.9/generated/torch.xpu.get_device_capability.html
index 7955c458d79..8e282cdf6a6 100644
--- a/2.9/generated/torch.xpu.get_device_capability.html
+++ b/2.9/generated/torch.xpu.get_device_capability.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.get_device_capability<a class="headerlink" href="#torch-xpu-get-device-capability" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.get_device_capability">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_device_capability</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_device_capability" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_device_capability</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L224"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_device_capability" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the xpu capability of a device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.get_device_name.html b/2.9/generated/torch.xpu.get_device_name.html
index 5f12bb1e275..c8ea6fba7f7 100644
--- a/2.9/generated/torch.xpu.get_device_name.html
+++ b/2.9/generated/torch.xpu.get_device_name.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.get_device_name<a class="headerlink" href="#torch-xpu-get-device-name" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.get_device_name">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_device_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L209"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_device_name" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_device_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L209"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_device_name" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the name of a device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.get_device_properties.html b/2.9/generated/torch.xpu.get_device_properties.html
index c92887f4853..4e13bac7b42 100644
--- a/2.9/generated/torch.xpu.get_device_properties.html
+++ b/2.9/generated/torch.xpu.get_device_properties.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.get_device_properties<a class="headerlink" href="#torch-xpu-get-device-properties" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.get_device_properties">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_device_properties</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_device_properties" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_device_properties</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L249"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_device_properties" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the properties of a device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.get_gencode_flags.html b/2.9/generated/torch.xpu.get_gencode_flags.html
index 2e9ff9d28f5..b60fc1c4acf 100644
--- a/2.9/generated/torch.xpu.get_gencode_flags.html
+++ b/2.9/generated/torch.xpu.get_gencode_flags.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.get_gencode_flags<a class="headerlink" href="#torch-xpu-get-gencode-flags" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.get_gencode_flags">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_gencode_flags</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_gencode_flags" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_gencode_flags</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L436"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_gencode_flags" title="Permalink to this definition">#</a></dt>
 <dd><p>Return XPU AOT(ahead-of-time) build flags this library was compiled with.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.xpu.get_rng_state.html b/2.9/generated/torch.xpu.get_rng_state.html
index e4e8918d88f..91d7a56e622 100644
--- a/2.9/generated/torch.xpu.get_rng_state.html
+++ b/2.9/generated/torch.xpu.get_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.get_rng_state<a class="headerlink" href="#torch-xpu-get-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.get_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'xpu'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'xpu'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L11"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the random number generator state of the specified GPU as a ByteTensor.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.get_rng_state_all.html b/2.9/generated/torch.xpu.get_rng_state_all.html
index ebb03bc9eeb..8b942a5feda 100644
--- a/2.9/generated/torch.xpu.get_rng_state_all.html
+++ b/2.9/generated/torch.xpu.get_rng_state_all.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.get_rng_state_all<a class="headerlink" href="#torch-xpu-get-rng-state-all" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.get_rng_state_all">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_rng_state_all</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_rng_state_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_rng_state_all</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L33"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_rng_state_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a list of ByteTensor representing the random number states of all devices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.xpu.get_stream_from_external.html b/2.9/generated/torch.xpu.get_stream_from_external.html
index 1040439c32e..9ce6c4100a4 100644
--- a/2.9/generated/torch.xpu.get_stream_from_external.html
+++ b/2.9/generated/torch.xpu.get_stream_from_external.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.get_stream_from_external<a class="headerlink" href="#torch-xpu-get-stream-from-external" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.get_stream_from_external">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_stream_from_external</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_ptr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L386"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_stream_from_external" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">get_stream_from_external</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_ptr</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L386"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.get_stream_from_external" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a <a class="reference internal" href="torch.xpu.Stream.html#torch.xpu.Stream" title="torch.xpu.Stream"><code class="xref py py-class docutils literal notranslate"><span class="pre">Stream</span></code></a> from an external SYCL queue.</p>
 <p>This function is used to wrap SYCL queue created in other libraries in order
 to facilitate data exchange and multi-library interactions.</p>
diff --git a/2.9/generated/torch.xpu.init.html b/2.9/generated/torch.xpu.init.html
index 83b4fb9d95f..7305c975cd9 100644
--- a/2.9/generated/torch.xpu.init.html
+++ b/2.9/generated/torch.xpu.init.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.init<a class="headerlink" href="#torch-xpu-init" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.init">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">init</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.init" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">init</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.init" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize PyTorch’s XPU state.
 This is a Python API about lazy initialization that avoids initializing
 XPU until the first time it is accessed. Does nothing if the XPU state is
diff --git a/2.9/generated/torch.xpu.initial_seed.html b/2.9/generated/torch.xpu.initial_seed.html
index 099dfaf269f..6bb91eeb552 100644
--- a/2.9/generated/torch.xpu.initial_seed.html
+++ b/2.9/generated/torch.xpu.initial_seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.initial_seed<a class="headerlink" href="#torch-xpu-initial-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.initial_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">initial_seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.initial_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">initial_seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.initial_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current random seed of the current GPU.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
diff --git a/2.9/generated/torch.xpu.is_available.html b/2.9/generated/torch.xpu.is_available.html
index 68fb5968390..16d021639db 100644
--- a/2.9/generated/torch.xpu.is_available.html
+++ b/2.9/generated/torch.xpu.is_available.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.is_available<a class="headerlink" href="#torch-xpu-is-available" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a bool indicating if XPU is currently available.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.xpu.is_initialized.html b/2.9/generated/torch.xpu.is_initialized.html
index fa100a07af4..d3b7c2c2f7e 100644
--- a/2.9/generated/torch.xpu.is_initialized.html
+++ b/2.9/generated/torch.xpu.is_initialized.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.is_initialized<a class="headerlink" href="#torch-xpu-is-initialized" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.is_initialized">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">is_initialized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.is_initialized" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">is_initialized</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L80"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.is_initialized" title="Permalink to this definition">#</a></dt>
 <dd><p>Return whether PyTorch’s XPU state has been initialized.</p>
 </dd></dl>
 
diff --git a/2.9/generated/torch.xpu.manual_seed.html b/2.9/generated/torch.xpu.manual_seed.html
index 4043b182b5e..9f048925a8c 100644
--- a/2.9/generated/torch.xpu.manual_seed.html
+++ b/2.9/generated/torch.xpu.manual_seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.manual_seed<a class="headerlink" href="#torch-xpu-manual-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.manual_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.manual_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.manual_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the seed for generating random numbers for the current GPU.</p>
 <p>It’s safe to call this function if XPU is not available; in that case, it is silently ignored.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.xpu.manual_seed_all.html b/2.9/generated/torch.xpu.manual_seed_all.html
index d22d3fce9aa..ca164755683 100644
--- a/2.9/generated/torch.xpu.manual_seed_all.html
+++ b/2.9/generated/torch.xpu.manual_seed_all.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.manual_seed_all<a class="headerlink" href="#torch-xpu-manual-seed-all" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.manual_seed_all">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">manual_seed_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.manual_seed_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">manual_seed_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L98"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.manual_seed_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the seed for generating random numbers on all GPUs.</p>
 <p>It’s safe to call this function if XPU is not available; in that case, it is silently ignored.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.xpu.memory.empty_cache.html b/2.9/generated/torch.xpu.memory.empty_cache.html
index d03bd6877de..ebdded7f133 100644
--- a/2.9/generated/torch.xpu.memory.empty_cache.html
+++ b/2.9/generated/torch.xpu.memory.empty_cache.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.empty_cache<a class="headerlink" href="#torch-xpu-memory-empty-cache" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.empty_cache">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.empty_cache" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">empty_cache</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.empty_cache" title="Permalink to this definition">#</a></dt>
 <dd><p>Release all unoccupied cached memory currently held by the caching
 allocator so that those can be used in other XPU application.</p>
 <div class="admonition note">
diff --git a/2.9/generated/torch.xpu.memory.max_memory_allocated.html b/2.9/generated/torch.xpu.memory.max_memory_allocated.html
index c56e44fa9b3..789574726a0 100644
--- a/2.9/generated/torch.xpu.memory.max_memory_allocated.html
+++ b/2.9/generated/torch.xpu.memory.max_memory_allocated.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.max_memory_allocated<a class="headerlink" href="#torch-xpu-memory-max-memory-allocated" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.max_memory_allocated">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.max_memory_allocated" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.max_memory_allocated" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the maximum GPU memory occupied by tensors in bytes for a given device.</p>
 <p>By default, this returns the peak allocated memory since the beginning of
 this program. <code class="xref py py-func docutils literal notranslate"><span class="pre">reset_peak_memory_stats()</span></code> can be used to
diff --git a/2.9/generated/torch.xpu.memory.max_memory_reserved.html b/2.9/generated/torch.xpu.memory.max_memory_reserved.html
index 3aba7dccb58..d6828e858ee 100644
--- a/2.9/generated/torch.xpu.memory.max_memory_reserved.html
+++ b/2.9/generated/torch.xpu.memory.max_memory_reserved.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.max_memory_reserved<a class="headerlink" href="#torch-xpu-memory-max-memory-reserved" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.max_memory_reserved">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.max_memory_reserved" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">max_memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.max_memory_reserved" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the maximum GPU memory managed by the caching allocator in bytes for a given device.</p>
 <p>By default, this returns the peak cached memory since the beginning of this
 program. <code class="xref py py-func docutils literal notranslate"><span class="pre">reset_peak_memory_stats()</span></code> can be used to reset
diff --git a/2.9/generated/torch.xpu.memory.mem_get_info.html b/2.9/generated/torch.xpu.memory.mem_get_info.html
index 8341255b0a8..a6ea6ec92de 100644
--- a/2.9/generated/torch.xpu.memory.mem_get_info.html
+++ b/2.9/generated/torch.xpu.memory.mem_get_info.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.mem_get_info<a class="headerlink" href="#torch-xpu-memory-mem-get-info" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.mem_get_info">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">mem_get_info</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.mem_get_info" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">mem_get_info</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L181"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.mem_get_info" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the global free and total GPU memory for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.memory.memory_allocated.html b/2.9/generated/torch.xpu.memory.memory_allocated.html
index 520881a1c4c..f7c92534148 100644
--- a/2.9/generated/torch.xpu.memory.memory_allocated.html
+++ b/2.9/generated/torch.xpu.memory.memory_allocated.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.memory_allocated<a class="headerlink" href="#torch-xpu-memory-memory-allocated" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.memory_allocated">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.memory_allocated" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">memory_allocated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L120"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.memory_allocated" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current GPU memory occupied by tensors in bytes for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.memory.memory_reserved.html b/2.9/generated/torch.xpu.memory.memory_reserved.html
index b5e16ad7376..59e718749f4 100644
--- a/2.9/generated/torch.xpu.memory.memory_reserved.html
+++ b/2.9/generated/torch.xpu.memory.memory_reserved.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.memory_reserved<a class="headerlink" href="#torch-xpu-memory-memory-reserved" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.memory_reserved">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.memory_reserved" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">memory_reserved</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.memory_reserved" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current GPU memory managed by the caching allocator in bytes for a given device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.memory.memory_stats.html b/2.9/generated/torch.xpu.memory.memory_stats.html
index 6577067ebb6..baa016795dd 100644
--- a/2.9/generated/torch.xpu.memory.memory_stats.html
+++ b/2.9/generated/torch.xpu.memory.memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.memory_stats<a class="headerlink" href="#torch-xpu-memory-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L64"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dictionary of XPU memory allocator statistics for a given device.</p>
 <p>The return value of this function is a dictionary of statistics, each of
 which is a non-negative integer.</p>
diff --git a/2.9/generated/torch.xpu.memory.memory_stats_as_nested_dict.html b/2.9/generated/torch.xpu.memory.memory_stats_as_nested_dict.html
index ba5a6ad6bc4..70c5a16f960 100644
--- a/2.9/generated/torch.xpu.memory.memory_stats_as_nested_dict.html
+++ b/2.9/generated/torch.xpu.memory.memory_stats_as_nested_dict.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.memory_stats_as_nested_dict<a class="headerlink" href="#torch-xpu-memory-memory-stats-as-nested-dict" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.memory_stats_as_nested_dict">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats_as_nested_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.memory_stats_as_nested_dict" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">memory_stats_as_nested_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L56"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.memory_stats_as_nested_dict" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the result of <code class="xref py py-func docutils literal notranslate"><span class="pre">memory_stats()</span></code> as a nested dictionary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/generated/torch.xpu.memory.reset_accumulated_memory_stats.html b/2.9/generated/torch.xpu.memory.reset_accumulated_memory_stats.html
index 0737f08b7f5..6cd9093a07d 100644
--- a/2.9/generated/torch.xpu.memory.reset_accumulated_memory_stats.html
+++ b/2.9/generated/torch.xpu.memory.reset_accumulated_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.reset_accumulated_memory_stats<a class="headerlink" href="#torch-xpu-memory-reset-accumulated-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.reset_accumulated_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">reset_accumulated_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.reset_accumulated_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">reset_accumulated_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.reset_accumulated_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the “accumulated” (historical) stats tracked by the XPU memory allocator.</p>
 <p>See <code class="xref py py-func docutils literal notranslate"><span class="pre">memory_stats()</span></code> for details. Accumulated stats correspond to
 the <cite>“allocated”</cite> and <cite>“freed”</cite> keys in each individual stat dict.</p>
diff --git a/2.9/generated/torch.xpu.memory.reset_peak_memory_stats.html b/2.9/generated/torch.xpu.memory.reset_peak_memory_stats.html
index 4da8260331b..91db45db915 100644
--- a/2.9/generated/torch.xpu.memory.reset_peak_memory_stats.html
+++ b/2.9/generated/torch.xpu.memory.reset_peak_memory_stats.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.memory.reset_peak_memory_stats<a class="headerlink" href="#torch-xpu-memory-reset-peak-memory-stats" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.memory.reset_peak_memory_stats">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">reset_peak_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/memory.py#L26"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.reset_peak_memory_stats" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.memory.</span></span><span class="sig-name descname"><span class="pre">reset_peak_memory_stats</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/memory.py#L26"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.memory.reset_peak_memory_stats" title="Permalink to this definition">#</a></dt>
 <dd><p>Reset the “peak” stats tracked by the XPU memory allocator.</p>
 <p>See <code class="xref py py-func docutils literal notranslate"><span class="pre">memory_stats()</span></code> for details. Peak stats correspond to the
 <cite>“peak”</cite> key in each individual stat dict.</p>
diff --git a/2.9/generated/torch.xpu.seed.html b/2.9/generated/torch.xpu.seed.html
index fe9482071ff..aae1a87248a 100644
--- a/2.9/generated/torch.xpu.seed.html
+++ b/2.9/generated/torch.xpu.seed.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.seed<a class="headerlink" href="#torch-xpu-seed" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.seed">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L116"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the seed for generating random numbers to a random number for the current GPU.</p>
 <p>It’s safe to call this function if XPU is not available; in that case, it is silently ignored.</p>
 <div class="admonition warning">
diff --git a/2.9/generated/torch.xpu.seed_all.html b/2.9/generated/torch.xpu.seed_all.html
index 7099756abc6..b780f4368d4 100644
--- a/2.9/generated/torch.xpu.seed_all.html
+++ b/2.9/generated/torch.xpu.seed_all.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.seed_all<a class="headerlink" href="#torch-xpu-seed-all" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.seed_all">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">seed_all</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.seed_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">seed_all</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.seed_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the seed for generating random numbers to a random number on all GPUs.</p>
 <p>It’s safe to call this function if XPU is not available; in that case, it is silently ignored.</p>
 <dl class="field-list simple">
diff --git a/2.9/generated/torch.xpu.set_device.html b/2.9/generated/torch.xpu.set_device.html
index 8d3e3726cd2..caa77834cf6 100644
--- a/2.9/generated/torch.xpu.set_device.html
+++ b/2.9/generated/torch.xpu.set_device.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.set_device<a class="headerlink" href="#torch-xpu-set-device" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.set_device">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">set_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.set_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">set_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.set_device" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the current device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.set_rng_state.html b/2.9/generated/torch.xpu.set_rng_state.html
index 15d16f01d17..38bd3b2b2dd 100644
--- a/2.9/generated/torch.xpu.set_rng_state.html
+++ b/2.9/generated/torch.xpu.set_rng_state.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.set_rng_state<a class="headerlink" href="#torch-xpu-set-rng-state" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.set_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'xpu'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.set_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'xpu'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L39"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.set_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the random number generator state of the specified GPU.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.set_rng_state_all.html b/2.9/generated/torch.xpu.set_rng_state_all.html
index f76abf775b4..84ba3c72a73 100644
--- a/2.9/generated/torch.xpu.set_rng_state_all.html
+++ b/2.9/generated/torch.xpu.set_rng_state_all.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.set_rng_state_all<a class="headerlink" href="#torch-xpu-set-rng-state-all" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.set_rng_state_all">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">set_rng_state_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_states</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/random.py#L66"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.set_rng_state_all" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">set_rng_state_all</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_states</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/random.py#L66"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.set_rng_state_all" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the random number generator state of all devices.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.set_stream.html b/2.9/generated/torch.xpu.set_stream.html
index d02d3ee6e7d..2a191492211 100644
--- a/2.9/generated/torch.xpu.set_stream.html
+++ b/2.9/generated/torch.xpu.set_stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.set_stream<a class="headerlink" href="#torch-xpu-set-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.set_stream">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">set_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.set_stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">set_stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.set_stream" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Set the current stream.This is a wrapper API to set the stream.</dt><dd><p>Usage of this function is discouraged in favor of the <code class="docutils literal notranslate"><span class="pre">stream</span></code>
 context manager.</p>
diff --git a/2.9/generated/torch.xpu.stream.html b/2.9/generated/torch.xpu.stream.html
index 0e223d602cb..3c0f300f2ab 100644
--- a/2.9/generated/torch.xpu.stream.html
+++ b/2.9/generated/torch.xpu.stream.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.stream<a class="headerlink" href="#torch-xpu-stream" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.stream">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.stream" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">stream</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">stream</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L326"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.stream" title="Permalink to this definition">#</a></dt>
 <dd><p>Wrap around the Context-manager StreamContext that selects a given stream.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/generated/torch.xpu.synchronize.html b/2.9/generated/torch.xpu.synchronize.html
index 904521033b1..f645ef15ff7 100644
--- a/2.9/generated/torch.xpu.synchronize.html
+++ b/2.9/generated/torch.xpu.synchronize.html
@@ -4404,7 +4404,7 @@
 <h1>torch.xpu.synchronize<a class="headerlink" href="#torch-xpu-synchronize" title="Permalink to this heading">#</a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.xpu.synchronize">
-<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/xpu/__init__.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.synchronize" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.xpu.</span></span><span class="sig-name descname"><span class="pre">synchronize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/xpu/__init__.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.xpu.synchronize" title="Permalink to this definition">#</a></dt>
 <dd><p>Wait for all kernels in all streams on a XPU device to complete.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/hub.html b/2.9/hub.html
index 0e33f719470..0c39fd565fb 100644
--- a/2.9/hub.html
+++ b/2.9/hub.html
@@ -4469,7 +4469,7 @@ <h2>Loading models from Hub<a class="headerlink" href="#loading-models-from-hub"
 <a class="reference internal" href="#torch.hub.load" title="torch.hub.load"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.hub.load()</span></code></a>.</p>
 <span class="target" id="module-torch.hub"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.hub.list">
-<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">github</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_reload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_validation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trust_repo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/hub.py#L427"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.list" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">github</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_reload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_validation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trust_repo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/hub.py#L427"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.list" title="Permalink to this definition">#</a></dt>
 <dd><p>List all callable entrypoints available in the repo specified by <code class="docutils literal notranslate"><span class="pre">github</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4522,7 +4522,7 @@ <h2>Loading models from Hub<a class="headerlink" href="#loading-models-from-hub"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.hub.help">
-<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">help</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">github</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_reload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_validation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trust_repo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/hub.py#L499"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.help" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">help</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">github</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_reload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_validation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trust_repo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/hub.py#L499"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.help" title="Permalink to this definition">#</a></dt>
 <dd><p>Show the docstring of entrypoint <code class="docutils literal notranslate"><span class="pre">model</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4567,7 +4567,7 @@ <h2>Loading models from Hub<a class="headerlink" href="#loading-models-from-hub"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.hub.load">
-<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">repo_or_dir</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'github'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trust_repo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_reload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_validation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/hub.py#L554"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.load" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">load</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">repo_or_dir</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'github'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">trust_repo</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">force_reload</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_validation</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/hub.py#L554"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.load" title="Permalink to this definition">#</a></dt>
 <dd><p>Load a model from a github repo or a local directory.</p>
 <p>Note: Loading a model is the typical use case, but this can also be used to
 for loading other objects such as tokenizers, loss functions, etc.</p>
@@ -4641,7 +4641,7 @@ <h2>Loading models from Hub<a class="headerlink" href="#loading-models-from-hub"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.hub.download_url_to_file">
-<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">download_url_to_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">url</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hash_prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">progress</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/hub.py#L690"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.download_url_to_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">download_url_to_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">url</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hash_prefix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">progress</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/hub.py#L690"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.download_url_to_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Download object at the given URL to a local path.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4666,7 +4666,7 @@ <h2>Loading models from Hub<a class="headerlink" href="#loading-models-from-hub"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.hub.load_state_dict_from_url">
-<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">load_state_dict_from_url</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">url</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">progress</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_hash</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weights_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/hub.py#L812"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.load_state_dict_from_url" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">load_state_dict_from_url</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">url</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">progress</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_hash</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weights_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/hub.py#L812"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.load_state_dict_from_url" title="Permalink to this definition">#</a></dt>
 <dd><p>Loads the Torch serialized object at the given URL.</p>
 <p>If downloaded file is a zip file, it will be automatically
 decompressed.</p>
@@ -4729,7 +4729,7 @@ <h3>Where are my downloaded models saved?<a class="headerlink" href="#where-are-
 </ul>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.hub.get_dir">
-<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">get_dir</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/hub.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.get_dir" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">get_dir</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/hub.py#L397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.get_dir" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the Torch Hub cache directory used for storing downloaded models &amp; weights.</p>
 <p>If <a class="reference internal" href="#torch.hub.set_dir" title="torch.hub.set_dir"><code class="xref py py-func docutils literal notranslate"><span class="pre">set_dir()</span></code></a> is not called, default path is <code class="docutils literal notranslate"><span class="pre">$TORCH_HOME/hub</span></code> where
 environment variable <code class="docutils literal notranslate"><span class="pre">$TORCH_HOME</span></code> defaults to <code class="docutils literal notranslate"><span class="pre">$XDG_CACHE_HOME/torch</span></code>.
@@ -4745,7 +4745,7 @@ <h3>Where are my downloaded models saved?<a class="headerlink" href="#where-are-
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.hub.set_dir">
-<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">set_dir</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/hub.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.set_dir" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.hub.</span></span><span class="sig-name descname"><span class="pre">set_dir</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">d</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/hub.py#L416"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.hub.set_dir" title="Permalink to this definition">#</a></dt>
 <dd><p>Optionally set the Torch Hub directory used to save downloaded models &amp; weights.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/library.html b/2.9/library.html
index ebd25f55752..4dd20c7482a 100644
--- a/2.9/library.html
+++ b/2.9/library.html
@@ -4409,7 +4409,7 @@ <h2>Testing custom ops<a class="headerlink" href="#testing-custom-ops" title="Pe
 mathematically correct.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.opcheck">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">opcheck</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_utils</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">('test_schema',</span> <span class="pre">'test_autograd_registration',</span> <span class="pre">'test_faketensor',</span> <span class="pre">'test_aot_dispatch_dynamic')</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raise_exception</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L1561"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.opcheck" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">opcheck</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">test_utils</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">('test_schema',</span> <span class="pre">'test_autograd_registration',</span> <span class="pre">'test_faketensor',</span> <span class="pre">'test_aot_dispatch_dynamic')</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raise_exception</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L1561"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.opcheck" title="Permalink to this definition">#</a></dt>
 <dd><p>Given an operator and some sample arguments, tests if the operator is
 registered correctly.</p>
 <p>That is, when you use the torch.library/TORCH_LIBRARY APIs to create a
@@ -4527,7 +4527,7 @@ <h2>Creating new custom ops in Python<a class="headerlink" href="#creating-new-c
 <p>Use <a class="reference internal" href="#torch.library.custom_op" title="torch.library.custom_op"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.library.custom_op()</span></code></a> to create new custom ops.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.custom_op">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">custom_op</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mutates_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_types</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_library/custom_ops.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.custom_op" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">custom_op</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mutates_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_types</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_library/custom_ops.py#L46"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.custom_op" title="Permalink to this definition">#</a></dt>
 <dd><p>Wraps a function into custom operator.</p>
 <p>Reasons why you may want to create a custom op include:
 - Wrapping a third-party library or custom kernel to work with PyTorch
@@ -4625,7 +4625,7 @@ <h2>Creating new custom ops in Python<a class="headerlink" href="#creating-new-c
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.triton_op">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">triton_op</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mutates_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_library/triton.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.triton_op" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">triton_op</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mutates_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_library/triton.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.triton_op" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a custom operator whose implementation is backed by 1+ triton kernels.</p>
 <p>This is a more structured way of using triton kernels with PyTorch.
 Prefer using triton kernels with no <code class="docutils literal notranslate"><span class="pre">torch.library</span></code> custom operator wrappers
@@ -4719,7 +4719,7 @@ <h2>Creating new custom ops in Python<a class="headerlink" href="#creating-new-c
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.wrap_triton">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">wrap_triton</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">triton_kernel</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_library/triton.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.wrap_triton" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">wrap_triton</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">triton_kernel</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_library/triton.py#L294"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.wrap_triton" title="Permalink to this definition">#</a></dt>
 <dd><p>Allows capture of a triton kernel into a graph via make_fx or
 non-strict <code class="docutils literal notranslate"><span class="pre">torch.export</span></code>.</p>
 <p>These technologies perform Dispatcher-based tracing (via
@@ -4792,7 +4792,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 via PyTorch’s C++ operator registration APIs).</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.register_kernel">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_kernel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_types</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_kernel" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_kernel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_types</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L776"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_kernel" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an implementation for a device type for this operator.</p>
 <p>Some valid device_types are: “cpu”, “cuda”, “xla”, “mps”, “ipu”, “xpu”.
 This API may be used as a decorator.</p>
@@ -4841,7 +4841,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.register_autocast">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_autocast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_inputs</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L844"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_autocast" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_autocast</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cast_inputs</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L844"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_autocast" title="Permalink to this definition">#</a></dt>
 <dd><p>Register an autocast dispatch rule for this custom op.</p>
 <p>Valid <cite>device_type</cite> include: “cpu” and “cuda”.</p>
 <dl class="field-list simple">
@@ -4883,7 +4883,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.register_autograd">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_autograd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backward</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">setup_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L1075"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_autograd" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_autograd</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backward</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">setup_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L1075"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_autograd" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a backward formula for this custom op.</p>
 <p>In order for an operator to work with autograd, you need to register
 a backward formula:
@@ -4967,7 +4967,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.register_fake">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_fake</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L939"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_fake" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_fake</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L939"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_fake" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a FakeTensor implementation (“fake impl”) for this operator.</p>
 <p>Also sometimes known as a “meta kernel”, “abstract impl”.</p>
 <p>An “FakeTensor implementation” specifies the behavior of this operator on
@@ -5062,7 +5062,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.register_vmap">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L1286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_vmap" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_vmap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L1286"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_vmap" title="Permalink to this definition">#</a></dt>
 <dd><p>Register a vmap implementation to support <a class="reference internal" href="generated/torch.vmap.html#torch.vmap" title="torch.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.vmap()</span></code></a> for this custom op.</p>
 <p>This API may be used as a decorator (see examples).</p>
 <p>In order for an operator to work with <a class="reference internal" href="generated/torch.vmap.html#torch.vmap" title="torch.vmap"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.vmap()</span></code></a>, you may need to register a
@@ -5140,14 +5140,14 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.impl_abstract">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">impl_abstract</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qualname</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L757"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.impl_abstract" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">impl_abstract</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qualname</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_stacklevel</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L757"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.impl_abstract" title="Permalink to this definition">#</a></dt>
 <dd><p>This API was renamed to <a class="reference internal" href="#torch.library.register_fake" title="torch.library.register_fake"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.library.register_fake()</span></code></a> in PyTorch 2.4.
 Please use that instead.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.get_ctx">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">get_ctx</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L1470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.get_ctx" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">get_ctx</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L1470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.get_ctx" title="Permalink to this definition">#</a></dt>
 <dd><p>get_ctx() returns the current AbstractImplCtx object.</p>
 <p>Calling <code class="docutils literal notranslate"><span class="pre">get_ctx()</span></code> is only valid inside of an fake impl
 (see <a class="reference internal" href="#torch.library.register_fake" title="torch.library.register_fake"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.library.register_fake()</span></code></a> for more usage details.</p>
@@ -5160,7 +5160,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.register_torch_dispatch">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_torch_dispatch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">torch_dispatch_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L1205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_torch_dispatch" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">register_torch_dispatch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">torch_dispatch_class</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L1205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.register_torch_dispatch" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a torch_dispatch rule for the given operator and <code class="docutils literal notranslate"><span class="pre">torch_dispatch_class</span></code>.</p>
 <p>This allows for open registration to specify the behavior between the operator
 and the <code class="docutils literal notranslate"><span class="pre">torch_dispatch_class</span></code> without needing to modify the <code class="docutils literal notranslate"><span class="pre">torch_dispatch_class</span></code>
@@ -5204,7 +5204,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.infer_schema">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">infer_schema</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prototype_function</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mutates_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_library/infer_schema.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.infer_schema" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">infer_schema</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">prototype_function</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mutates_args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">op_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_library/infer_schema.py#L18"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.infer_schema" title="Permalink to this definition">#</a></dt>
 <dd><p>Parses the schema of a given function with type hints. The schema is inferred from the
 function’s type hints, and can be used to define a new operator.</p>
 <p>We make the following assumptions:</p>
@@ -5255,7 +5255,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch._library.custom_ops.CustomOpDef">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._library.custom_ops.</span></span><span class="sig-name descname"><span class="pre">CustomOpDef</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">namespace</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_library/custom_ops.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._library.custom_ops.CustomOpDef" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch._library.custom_ops.</span></span><span class="sig-name descname"><span class="pre">CustomOpDef</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">namespace</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_library/custom_ops.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._library.custom_ops.CustomOpDef" title="Permalink to this definition">#</a></dt>
 <dd><p>CustomOpDef is a wrapper around a function that turns it into a custom op.</p>
 <p>It has various methods for registering additional behavior for this
 custom op.</p>
@@ -5265,7 +5265,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch._library.custom_ops.CustomOpDef.set_kernel_enabled">
-<span class="sig-name descname"><span class="pre">set_kernel_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_library/custom_ops.py#L223"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._library.custom_ops.CustomOpDef.set_kernel_enabled" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_kernel_enabled</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device_type</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_library/custom_ops.py#L223"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._library.custom_ops.CustomOpDef.set_kernel_enabled" title="Permalink to this definition">#</a></dt>
 <dd><p>Disable or re-enable an already registered kernel for this custom operator.</p>
 <p>If the kernel is already disabled/enabled, this is a no-op.</p>
 <div class="admonition note">
@@ -5307,7 +5307,7 @@ <h2>Extending custom ops (created from Python or C++)<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.get_kernel">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">get_kernel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L1479"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.get_kernel" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">get_kernel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L1479"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.get_kernel" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the computed kernel for a given operator and dispatch key.</p>
 <p>This function retrieves the kernel that would be executed for a given
 operator and dispatch key combination. The returned SafeKernelFunction
@@ -5387,7 +5387,7 @@ <h2>Low-level APIs<a class="headerlink" href="#low-level-apis" title="Permalink
 <p>A tutorial that walks you through some examples on how to use this API is available on <a class="reference external" href="https://colab.research.google.com/drive/1RRhSfk7So3Cn02itzLWE9K4Fam-8U011?usp=sharing">Google Colab</a>.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.library.Library">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">Library</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ns</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kind</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.Library" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">Library</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ns</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kind</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.Library" title="Permalink to this definition">#</a></dt>
 <dd><p>A class to create libraries that can be used to register new operators or
 override operators in existing libraries from Python.
 A user can optionally pass in a dispatch keyname if they only want to register
@@ -5408,7 +5408,7 @@ <h2>Low-level APIs<a class="headerlink" href="#low-level-apis" title="Permalink
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.library.Library.define">
-<span class="sig-name descname"><span class="pre">define</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">schema</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alias_analysis</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.Library.define" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">define</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">schema</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alias_analysis</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.Library.define" title="Permalink to this definition">#</a></dt>
 <dd><p>Defines a new operator and its semantics in the ns namespace.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5435,7 +5435,7 @@ <h2>Low-level APIs<a class="headerlink" href="#low-level-apis" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.library.Library.fallback">
-<span class="sig-name descname"><span class="pre">fallback</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_keyset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.Library.fallback" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fallback</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_keyset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L374"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.Library.fallback" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers the function implementation as the fallback for the given key.</p>
 <p>This function only works for a library with global namespace (“_”).</p>
 <dl class="field-list simple">
@@ -5462,7 +5462,7 @@ <h2>Low-level APIs<a class="headerlink" href="#low-level-apis" title="Permalink
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.library.Library.impl">
-<span class="sig-name descname"><span class="pre">impl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_keyset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.Library.impl" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">impl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">op_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_keyset</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_override</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.Library.impl" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers the function implementation for an operator defined in the library.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5495,13 +5495,13 @@ <h2>Low-level APIs<a class="headerlink" href="#low-level-apis" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.fallthrough_kernel">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">fallthrough_kernel</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.fallthrough_kernel" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">fallthrough_kernel</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L69"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.fallthrough_kernel" title="Permalink to this definition">#</a></dt>
 <dd><p>A dummy function to pass to <code class="docutils literal notranslate"><span class="pre">Library.impl</span></code> in order to register a fallthrough.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.define">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">define</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qualname</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L480"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.define" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">define</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qualname</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tags</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L480"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.define" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">define</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lib</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schema</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">alias_analysis</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span></dt>
 <dd><p>Defines a new operator.</p>
@@ -5558,7 +5558,7 @@ <h2>Low-level APIs<a class="headerlink" href="#low-level-apis" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.library.impl">
-<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">impl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lib</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/library.py#L590"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.impl" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">impl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lib</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dispatch_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/library.py#L590"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.library.impl" title="Permalink to this definition">#</a></dt>
 <dt class="sig sig-object py">
 <span class="sig-prename descclassname"><span class="pre">torch.library.</span></span><span class="sig-name descname"><span class="pre">impl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">qualname</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">types</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Sequence</span><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Literal</span><span class="p"><span class="pre">[</span></span><span class="pre">None</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lib</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="#torch.library.Library" title="torch.library.Library"><span class="pre">Library</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Callable</span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="pre">Callable</span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">...</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.14)"><span class="pre">object</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><span class="pre">None</span></a><span class="p"><span class="pre">]</span></span></span></span></dt>
 <dt class="sig sig-object py">
diff --git a/2.9/mobile_optimizer.html b/2.9/mobile_optimizer.html
index 9894b26c73a..ed2e6ef67d7 100644
--- a/2.9/mobile_optimizer.html
+++ b/2.9/mobile_optimizer.html
@@ -4405,7 +4405,7 @@ <h1>torch.utils.mobile_optimizer<a class="headerlink" href="#torch-utils-mobile-
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.mobile_optimizer.optimize_for_mobile">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.mobile_optimizer.</span></span><span class="sig-name descname"><span class="pre">optimize_for_mobile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">script_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimization_blocklist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserved_methods</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'CPU'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/mobile_optimizer.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.mobile_optimizer.optimize_for_mobile" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.mobile_optimizer.</span></span><span class="sig-name descname"><span class="pre">optimize_for_mobile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">script_module</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimization_blocklist</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">preserved_methods</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'CPU'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/mobile_optimizer.py#L15"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.mobile_optimizer.optimize_for_mobile" title="Permalink to this definition">#</a></dt>
 <dd><p>Optimize a torch script module for mobile deployment.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/model_zoo.html b/2.9/model_zoo.html
index 7c7935e2107..5e522f96f25 100644
--- a/2.9/model_zoo.html
+++ b/2.9/model_zoo.html
@@ -4397,7 +4397,7 @@ <h1>torch.utils.model_zoo<a class="headerlink" href="#torch-utils-model-zoo" tit
 <p>Moved to <code class="docutils literal notranslate"><span class="pre">torch.hub</span></code>.</p>
 <span class="target" id="module-torch.utils.model_zoo"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.utils.model_zoo.load_url">
-<span class="sig-prename descclassname"><span class="pre">torch.utils.model_zoo.</span></span><span class="sig-name descname"><span class="pre">load_url</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">url</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">progress</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_hash</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weights_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/hub.py#L812"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.model_zoo.load_url" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.utils.model_zoo.</span></span><span class="sig-name descname"><span class="pre">load_url</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">url</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">progress</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_hash</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weights_only</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/hub.py#L812"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.model_zoo.load_url" title="Permalink to this definition">#</a></dt>
 <dd><p>Loads the Torch serialized object at the given URL.</p>
 <p>If downloaded file is a zip file, it will be automatically
 decompressed.</p>
diff --git a/2.9/module_tracker.html b/2.9/module_tracker.html
index 972e82ad439..33672365493 100644
--- a/2.9/module_tracker.html
+++ b/2.9/module_tracker.html
@@ -4398,7 +4398,7 @@
 It can be used within other tracking tools to be able to easily associate measured quantities to user-friendly names. This is used in particular in the FlopCounterMode today.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.module_tracker.ModuleTracker">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.module_tracker.</span></span><span class="sig-name descname"><span class="pre">ModuleTracker</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/module_tracker.py#L25"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.module_tracker.ModuleTracker" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.module_tracker.</span></span><span class="sig-name descname"><span class="pre">ModuleTracker</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/module_tracker.py#L25"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.module_tracker.ModuleTracker" title="Permalink to this definition">#</a></dt>
 <dd><p><code class="docutils literal notranslate"><span class="pre">ModuleTracker</span></code> is a context manager that tracks the nn.Module hierarchy during execution
 so that other system can query which Module is currently being executed (or its backward is being
 executed).</p>
diff --git a/2.9/monitor.html b/2.9/monitor.html
index 66b19732dcf..350a04a914e 100644
--- a/2.9/monitor.html
+++ b/2.9/monitor.html
@@ -4571,7 +4571,7 @@ <h1>torch.monitor<a class="headerlink" href="#torch-monitor" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.monitor.TensorboardEventHandler">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.monitor.</span></span><span class="sig-name descname"><span class="pre">TensorboardEventHandler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">writer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/monitor/__init__.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.monitor.TensorboardEventHandler" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.monitor.</span></span><span class="sig-name descname"><span class="pre">TensorboardEventHandler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">writer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/monitor/__init__.py#L13"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.monitor.TensorboardEventHandler" title="Permalink to this definition">#</a></dt>
 <dd><p>TensorboardEventHandler is an event handler that will write known events to
 the provided SummaryWriter.</p>
 <p>This currently only supports <code class="docutils literal notranslate"><span class="pre">torch.monitor.Stat</span></code> events which are logged
@@ -4587,7 +4587,7 @@ <h1>torch.monitor<a class="headerlink" href="#torch-monitor" title="Permalink to
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.monitor.TensorboardEventHandler.__init__">
-<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">writer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/monitor/__init__.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.monitor.TensorboardEventHandler.__init__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">writer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/monitor/__init__.py#L30"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.monitor.TensorboardEventHandler.__init__" title="Permalink to this definition">#</a></dt>
 <dd><p>Constructs the <code class="docutils literal notranslate"><span class="pre">TensorboardEventHandler</span></code>.</p>
 <dl class="field-list simple">
 </dl>
diff --git a/2.9/multiprocessing.html b/2.9/multiprocessing.html
index 6e99b7d8574..097d66ec088 100644
--- a/2.9/multiprocessing.html
+++ b/2.9/multiprocessing.html
@@ -1643,19 +1643,19 @@
 <h2>Strategy management<a class="headerlink" href="#strategy-management" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.multiprocessing.get_all_sharing_strategies">
-<span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">get_all_sharing_strategies</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/multiprocessing/__init__.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.get_all_sharing_strategies" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">get_all_sharing_strategies</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/multiprocessing/__init__.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.get_all_sharing_strategies" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a set of sharing strategies supported on a current system.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.multiprocessing.get_sharing_strategy">
-<span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">get_sharing_strategy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/multiprocessing/__init__.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.get_sharing_strategy" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">get_sharing_strategy</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/multiprocessing/__init__.py#L73"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.get_sharing_strategy" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the current strategy for sharing CPU tensors.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.multiprocessing.set_sharing_strategy">
-<span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">set_sharing_strategy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_strategy</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/multiprocessing/__init__.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.set_sharing_strategy" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">set_sharing_strategy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_strategy</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/multiprocessing/__init__.py#L61"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.set_sharing_strategy" title="Permalink to this definition">#</a></dt>
 <dd><p>Set the strategy for sharing CPU tensors.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -1794,7 +1794,7 @@ <h2>Spawning subprocesses<a class="headerlink" href="#spawning-subprocesses" tit
 terminate processes upon detecting an error in one of them.</p>
 <span class="target" id="module-torch.multiprocessing.spawn"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.multiprocessing.spawn.spawn">
-<span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.spawn.</span></span><span class="sig-name descname"><span class="pre">spawn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nprocs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">join</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">daemon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'spawn'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/multiprocessing/spawn.py#L324"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.spawn.spawn" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.spawn.</span></span><span class="sig-name descname"><span class="pre">spawn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nprocs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">join</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">daemon</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'spawn'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/multiprocessing/spawn.py#L324"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.spawn.spawn" title="Permalink to this definition">#</a></dt>
 <dd><p>Spawns <code class="docutils literal notranslate"><span class="pre">nprocs</span></code> processes that run <code class="docutils literal notranslate"><span class="pre">fn</span></code> with <code class="docutils literal notranslate"><span class="pre">args</span></code>.</p>
 <p>If one of the processes exits with a non-zero exit status, the
 remaining processes are killed and an exception is raised with the
@@ -1831,11 +1831,11 @@ <h2>Spawning subprocesses<a class="headerlink" href="#spawning-subprocesses" tit
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.multiprocessing.SpawnContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">SpawnContext</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/multiprocessing/spawn.py#L223"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.SpawnContext" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.multiprocessing.</span></span><span class="sig-name descname"><span class="pre">SpawnContext</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/multiprocessing/spawn.py#L223"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.SpawnContext" title="Permalink to this definition">#</a></dt>
 <dd><p>Returned by <a class="reference internal" href="#module-torch.multiprocessing.spawn" title="torch.multiprocessing.spawn"><code class="xref py py-func docutils literal notranslate"><span class="pre">spawn()</span></code></a> when called with <code class="docutils literal notranslate"><span class="pre">join=False</span></code>.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.multiprocessing.SpawnContext.join">
-<span class="sig-name descname"><span class="pre">join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grace_period</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/multiprocessing/spawn.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.SpawnContext.join" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">grace_period</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/multiprocessing/spawn.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.multiprocessing.SpawnContext.join" title="Permalink to this definition">#</a></dt>
 <dd><p>Join one or more processes within spawn context.</p>
 <p>Attempt to join one or more processes in this spawn context.
 If one of them exited with a non-zero exit status, this function
diff --git a/2.9/named_tensor.html b/2.9/named_tensor.html
index b41b6017ccb..56fc908b8f5 100644
--- a/2.9/named_tensor.html
+++ b/2.9/named_tensor.html
@@ -4663,7 +4663,7 @@ <h2>Named tensor API reference<a class="headerlink" href="#named-tensor-api-refe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.rename">
-<span class="sig-name descname"><span class="pre">rename</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">names</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">rename_map</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1435"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.rename" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rename</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">names</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">rename_map</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1435"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.rename" title="Permalink to this definition">#</a></dt>
 <dd><p>Renames dimension names of <code class="xref py py-attr docutils literal notranslate"><span class="pre">self</span></code>.</p>
 <p>There are two main usages:</p>
 <p><code class="docutils literal notranslate"><span class="pre">self.rename(**rename_map)</span></code> returns a view on tensor that has dims
@@ -4696,13 +4696,13 @@ <h2>Named tensor API reference<a class="headerlink" href="#named-tensor-api-refe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.rename_">
-<span class="sig-name descname"><span class="pre">rename_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">names</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">rename_map</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1420"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.rename_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">rename_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">names</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">rename_map</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1420"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.rename_" title="Permalink to this definition">#</a></dt>
 <dd><p>In-place version of <a class="reference internal" href="#torch.Tensor.rename" title="torch.Tensor.rename"><code class="xref py py-meth docutils literal notranslate"><span class="pre">rename()</span></code></a>.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.refine_names">
-<span class="sig-name descname"><span class="pre">refine_names</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">names</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.refine_names" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">refine_names</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">names</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.refine_names" title="Permalink to this definition">#</a></dt>
 <dd><p>Refines the dimension names of <code class="xref py py-attr docutils literal notranslate"><span class="pre">self</span></code> according to <a class="reference internal" href="#torch.Tensor.names" title="torch.Tensor.names"><code class="xref py py-attr docutils literal notranslate"><span class="pre">names</span></code></a>.</p>
 <p>Refining is a special case of renaming that “lifts” unnamed dimensions.
 A <code class="docutils literal notranslate"><span class="pre">None</span></code> dim can be refined to have any name; a named dim can only be
@@ -4784,7 +4784,7 @@ <h2>Named tensor API reference<a class="headerlink" href="#named-tensor-api-refe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.Tensor.align_to">
-<span class="sig-name descname"><span class="pre">align_to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">names</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_tensor.py#L1353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.align_to" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">align_to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">names</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_tensor.py#L1353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.Tensor.align_to" title="Permalink to this definition">#</a></dt>
 <dd><p>Permutes the dimensions of the <code class="xref py py-attr docutils literal notranslate"><span class="pre">self</span></code> tensor to match the order
 specified in <a class="reference internal" href="#torch.Tensor.names" title="torch.Tensor.names"><code class="xref py py-attr docutils literal notranslate"><span class="pre">names</span></code></a>, adding size-one dims for any new names.</p>
 <p>All of the dims of <code class="xref py py-attr docutils literal notranslate"><span class="pre">self</span></code> must be named in order to use this method.
diff --git a/2.9/nested.html b/2.9/nested.html
index 59082aef576..f8669effc21 100644
--- a/2.9/nested.html
+++ b/2.9/nested.html
@@ -4833,7 +4833,7 @@ <h3>Data dependent operation within torch.compile<a class="headerlink" href="#da
 <span id="construction-and-conversion"></span><h2>Detailed Docs for Construction and Conversion Functions<a class="headerlink" href="#detailed-docs-for-construction-and-conversion-functions" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nested.nested_tensor">
-<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">nested_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor_list</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pin_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nested/__init__.py#L210"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.nested_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">nested_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor_list</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pin_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nested/__init__.py#L210"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.nested_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Constructs a nested tensor with no autograd history (also known as a “leaf tensor”, see
 <a class="reference internal" href="notes/autograd.html#autograd-mechanics"><span class="std std-ref">Autograd mechanics</span></a>) from <code class="xref py py-attr docutils literal notranslate"><span class="pre">tensor_list</span></code> a list of tensors.</p>
 <dl class="field-list simple">
@@ -4873,7 +4873,7 @@ <h3>Data dependent operation within torch.compile<a class="headerlink" href="#da
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nested.nested_tensor_from_jagged">
-<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">nested_tensor_from_jagged</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offsets</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">jagged_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_seqlen</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_seqlen</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nested/__init__.py#L359"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.nested_tensor_from_jagged" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">nested_tensor_from_jagged</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">offsets</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lengths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">jagged_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_seqlen</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_seqlen</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nested/__init__.py#L359"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.nested_tensor_from_jagged" title="Permalink to this definition">#</a></dt>
 <dd><p>Constructs a jagged layout nested tensor from the given jagged components. The jagged layout
 consists of a required values buffer with the jagged dimension packed into a single dimension.
 The offsets / lengths metadata determines how this dimension is split into batch elements
@@ -4949,7 +4949,7 @@ <h3>Data dependent operation within torch.compile<a class="headerlink" href="#da
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nested.as_nested_tensor">
-<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">as_nested_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nested/__init__.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.as_nested_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">as_nested_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ts</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nested/__init__.py#L27"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.as_nested_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Constructs a nested tensor preserving autograd history from a tensor or a list / tuple of
 tensors.</p>
 <p>If a nested tensor is passed, it will be returned directly unless the device / dtype / layout
@@ -5054,7 +5054,7 @@ <h3>Data dependent operation within torch.compile<a class="headerlink" href="#da
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nested.masked_select">
-<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">masked_select</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nested/__init__.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.masked_select" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">masked_select</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nested/__init__.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.masked_select" title="Permalink to this definition">#</a></dt>
 <dd><p>Constructs a nested tensor given a strided tensor input and a strided mask, the resulting jagged layout nested tensor
 will have values retain values where the mask is equal to True. The dimensionality of the mask is preserved and is
 represented with the offsets, this is unlike <a class="reference internal" href="#torch.nested.masked_select" title="torch.nested.masked_select"><code class="xref py py-func docutils literal notranslate"><span class="pre">masked_select()</span></code></a> where the output is collapsed to a 1D tensor.</p>
@@ -5090,7 +5090,7 @@ <h3>Data dependent operation within torch.compile<a class="headerlink" href="#da
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nested.narrow">
-<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">narrow</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">length</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nested/__init__.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.narrow" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nested.</span></span><span class="sig-name descname"><span class="pre">narrow</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">length</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.strided</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nested/__init__.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nested.narrow" title="Permalink to this definition">#</a></dt>
 <dd><p>Constructs a nested tensor (which might be a view) from <code class="xref py py-attr docutils literal notranslate"><span class="pre">tensor</span></code>, a strided tensor. This follows
 similar semantics to torch.Tensor.narrow, where in the <code class="xref py py-attr docutils literal notranslate"><span class="pre">dim</span></code>-th dimension the new nested tensor
 shows only the elements in the interval <cite>[start, start+length)</cite>. As nested representations
diff --git a/2.9/nn.attention.flex_attention.html b/2.9/nn.attention.flex_attention.html
index 6936c2af1aa..5ae65e3dd27 100644
--- a/2.9/nn.attention.flex_attention.html
+++ b/2.9/nn.attention.flex_attention.html
@@ -4405,7 +4405,7 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Jul 16, 2024 | Last Updated On: Sep 08, 2025</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.flex_attention">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">flex_attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">score_mod</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">block_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_gqa</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_lse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L1449"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.flex_attention" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">flex_attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">query</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">score_mod</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">block_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enable_gqa</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_lse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kernel_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">return_aux</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L1449"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.flex_attention" title="Permalink to this definition">#</a></dt>
 <dd><p>This function implements scaled dot product attention with an arbitrary attention score modification function.</p>
 <p>This function computes the scaled dot product attention between query, key, and value tensors with a user-defined
 attention score modification function. The attention score modification function will be applied after the attention
@@ -4493,7 +4493,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.AuxOutput">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">AuxOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.AuxOutput" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">AuxOutput</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L214"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.AuxOutput" title="Permalink to this definition">#</a></dt>
 <dd><p>Auxiliary outputs from flex_attention operation.</p>
 <p>Fields will be None if not requested, or contain the tensor if requested.</p>
 <dl class="field-list simple">
@@ -4502,7 +4502,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.AuxRequest">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">AuxRequest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.AuxRequest" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">AuxRequest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">lse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_scores</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L204"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.AuxRequest" title="Permalink to this definition">#</a></dt>
 <dd><p>Request which auxiliary outputs to compute from flex_attention.</p>
 <p>Each field is a boolean indicating whether that auxiliary output should be computed.</p>
 <dl class="field-list simple">
@@ -4513,7 +4513,7 @@
 <h2>BlockMask Utilities<a class="headerlink" href="#blockmask-utilities" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.create_block_mask">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">create_block_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mask_mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">B</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">H</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">Q_LEN</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">KV_LEN</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">BLOCK_SIZE</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_compile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L1027"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.create_block_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">create_block_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mask_mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">B</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">H</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">Q_LEN</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">KV_LEN</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">BLOCK_SIZE</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_compile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L1027"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.create_block_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>This function creates a block mask tuple from a mask_mod function.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4556,7 +4556,7 @@ <h2>BlockMask Utilities<a class="headerlink" href="#blockmask-utilities" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.create_mask">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">create_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">B</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">H</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">Q_LEN</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">KV_LEN</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L978"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.create_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">create_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mod_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">B</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">H</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">Q_LEN</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">KV_LEN</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L978"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.create_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>This function creates a mask tensor from a mod_fn function.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4580,7 +4580,7 @@ <h2>BlockMask Utilities<a class="headerlink" href="#blockmask-utilities" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.create_nested_block_mask">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">create_nested_block_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mask_mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">B</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">H</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q_nt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_nt</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">BLOCK_SIZE</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_compile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L1205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.create_nested_block_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">create_nested_block_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mask_mod</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">B</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">H</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q_nt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_nt</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">BLOCK_SIZE</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_compile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L1205"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.create_nested_block_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>This function creates a nested tensor compatible block mask tuple from a mask_mod
 function. The returned BlockMask will be on the device specified by the input nested tensor.</p>
 <dl class="field-list simple">
@@ -4652,7 +4652,7 @@ <h2>BlockMask Utilities<a class="headerlink" href="#blockmask-utilities" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.and_masks">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">and_masks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">mask_mods</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L922"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.and_masks" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">and_masks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">mask_mods</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L922"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.and_masks" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a mask_mod that’s the intersection of provided mask_mods</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4663,7 +4663,7 @@ <h2>BlockMask Utilities<a class="headerlink" href="#blockmask-utilities" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.or_masks">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">or_masks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">mask_mods</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L908"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.or_masks" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">or_masks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">mask_mods</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L908"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.or_masks" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a mask_mod that’s the union of provided mask_mods</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4674,7 +4674,7 @@ <h2>BlockMask Utilities<a class="headerlink" href="#blockmask-utilities" title="
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.noop_mask">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">noop_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">head</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token_q</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token_kv</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L314"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.noop_mask" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">noop_mask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">head</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token_q</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">token_kv</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L314"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.noop_mask" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a noop mask_mod</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4688,7 +4688,7 @@ <h2>BlockMask Utilities<a class="headerlink" href="#blockmask-utilities" title="
 <h2>FlexKernelOptions<a class="headerlink" href="#flexkerneloptions" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.FlexKernelOptions">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">FlexKernelOptions</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.FlexKernelOptions" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">FlexKernelOptions</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L87"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.FlexKernelOptions" title="Permalink to this definition">#</a></dt>
 <dd><p>Options for controlling the behavior of FlexAttention kernels.</p>
 <p>These options are passed to the underlying Triton kernels to control performance
 and numerical behavior. Most users will not need to specify these options as the
@@ -4857,7 +4857,7 @@ <h2>FlexKernelOptions<a class="headerlink" href="#flexkerneloptions" title="Perm
 <h2>BlockMask<a class="headerlink" href="#blockmask" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.BlockMask">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">BlockMask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seq_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_kv_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_kv_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_q_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_q_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">BLOCK_SIZE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask_mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L386"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.nn.attention.flex_attention.</span></span><span class="sig-name descname"><span class="pre">BlockMask</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seq_lengths</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_kv_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_kv_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_q_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_q_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">BLOCK_SIZE</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask_mod</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L386"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask" title="Permalink to this definition">#</a></dt>
 <dd><p>BlockMask is our format for representing a block-sparse attention mask.
 It is somewhat of a cross in-between BCSR and a non-sparse format.</p>
 <p><strong>Basics</strong></p>
@@ -4909,7 +4909,7 @@ <h2>BlockMask<a class="headerlink" href="#blockmask" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.BlockMask.as_tuple">
-<span class="sig-name descname"><span class="pre">as_tuple</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flatten</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.as_tuple" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">as_tuple</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flatten</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L570"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.as_tuple" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a tuple of the attributes of the BlockMask.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4920,7 +4920,7 @@ <h2>BlockMask<a class="headerlink" href="#blockmask" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.BlockMask.from_kv_blocks">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_kv_blocks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kv_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_kv_num_blocks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_kv_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">BLOCK_SIZE</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask_mod</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seq_lengths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_q_blocks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L496"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.from_kv_blocks" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_kv_blocks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">kv_num_blocks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_indices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_kv_num_blocks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">full_kv_indices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">BLOCK_SIZE</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">128</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mask_mod</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seq_lengths</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_q_blocks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L496"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.from_kv_blocks" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a BlockMask instance from key-value block information.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4985,7 +4985,7 @@ <h2>BlockMask<a class="headerlink" href="#blockmask" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.BlockMask.numel">
-<span class="sig-name descname"><span class="pre">numel</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L731"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.numel" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">numel</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L731"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.numel" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the number of elements (not accounting for sparsity) in the mask.</p>
 </dd></dl>
 
@@ -5011,7 +5011,7 @@ <h2>BlockMask<a class="headerlink" href="#blockmask" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.BlockMask.sparsity">
-<span class="sig-name descname"><span class="pre">sparsity</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L740"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.sparsity" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">sparsity</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L740"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.sparsity" title="Permalink to this definition">#</a></dt>
 <dd><p>Computes the percentage of blocks that are sparse (i.e. not computed)</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5022,7 +5022,7 @@ <h2>BlockMask<a class="headerlink" href="#blockmask" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.BlockMask.to">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L827"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.to" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L827"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.to" title="Permalink to this definition">#</a></dt>
 <dd><p>Moves the BlockMask to the specified device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5048,7 +5048,7 @@ <h2>BlockMask<a class="headerlink" href="#blockmask" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.BlockMask.to_dense">
-<span class="sig-name descname"><span class="pre">to_dense</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L751"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.to_dense" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_dense</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L751"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.to_dense" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a dense block that is equivalent to the block mask.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5059,7 +5059,7 @@ <h2>BlockMask<a class="headerlink" href="#blockmask" title="Permalink to this he
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.nn.attention.flex_attention.BlockMask.to_string">
-<span class="sig-name descname"><span class="pre">to_string</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">grid_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(20,</span> <span class="pre">20)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/attention/flex_attention.py#L761"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.to_string" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to_string</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">grid_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">(20,</span> <span class="pre">20)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limit</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/attention/flex_attention.py#L761"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.attention.flex_attention.BlockMask.to_string" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a string representation of the block mask. Quite nifty.</p>
 <p>If grid_size is -1, prints out an uncompressed version. Warning, it can be quite big!</p>
 </dd></dl>
diff --git a/2.9/nn.init.html b/2.9/nn.init.html
index f59562b73cf..83212a6eda7 100644
--- a/2.9/nn.init.html
+++ b/2.9/nn.init.html
@@ -4402,7 +4402,7 @@
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.calculate_gain">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">calculate_gain</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.calculate_gain" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">calculate_gain</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">param</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L139"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.calculate_gain" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the recommended gain value for the given nonlinearity function.</p>
 <p>The values are as follows:</p>
 <div class="pst-scrollable-table-container"><table class="table">
@@ -4490,7 +4490,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.uniform_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">uniform_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.uniform_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">uniform_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L213"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.uniform_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input Tensor with values drawn from the uniform distribution.</p>
 <p><span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="script">U</mi><mo stretchy="false">(</mo><mi>a</mi><mo separator="true">,</mo><mi>b</mi><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\mathcal{U}(a, b)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathcal" style="margin-right:0.09931em;">U</span><span class="mopen">(</span><span class="mord mathnormal">a</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord mathnormal">b</span><span class="mclose">)</span></span></span></span></span>.</p>
 <dl class="field-list simple">
@@ -4515,7 +4515,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.normal_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">normal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mean</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">std</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.normal_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">normal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mean</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">std</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L240"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.normal_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input Tensor with values drawn from the normal distribution.</p>
 <p><span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="script">N</mi><mo stretchy="false">(</mo><mtext>mean</mtext><mo separator="true">,</mo><msup><mtext>std</mtext><mn>2</mn></msup><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\mathcal{N}(\text{mean}, \text{std}^2)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1.1484em;vertical-align:-0.25em;"></span><span class="mord mathcal" style="margin-right:0.14736em;">N</span><span class="mopen">(</span><span class="mord text"><span class="mord">mean</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord text"><span class="mord">std</span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8984em;"><span style="top:-3.1473em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span>.</p>
 <dl class="field-list simple">
@@ -4540,7 +4540,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.constant_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">constant_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L298"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.constant_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">constant_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">val</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L298"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.constant_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input Tensor with the value <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mtext>val</mtext></mrow><annotation encoding="application/x-tex">\text{val}</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.6944em;"></span><span class="mord text"><span class="mord">val</span></span></span></span></span></span>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4562,7 +4562,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.ones_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">ones_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.ones_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">ones_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.ones_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input Tensor with the scalar value <cite>1</cite>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4581,7 +4581,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.zeros_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">zeros_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L329"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.zeros_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">zeros_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L329"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.zeros_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input Tensor with the scalar value <cite>0</cite>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4600,7 +4600,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.eye_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">eye_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.eye_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">eye_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.eye_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the 2-dimensional input <cite>Tensor</cite> with the identity matrix.</p>
 <p>Preserves the identity of the inputs in <cite>Linear</cite> layers, where as
 many inputs are preserved as possible.</p>
@@ -4621,7 +4621,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.dirac_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">dirac_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L363"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.dirac_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">dirac_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">groups</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L363"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.dirac_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the {3, 4, 5}-dimensional input <cite>Tensor</cite> with the Dirac delta function.</p>
 <p>Preserves the identity of the inputs in <cite>Convolutional</cite>
 layers, where as many input channels are preserved as possible. In case
@@ -4648,7 +4648,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.xavier_uniform_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">xavier_uniform_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gain</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.xavier_uniform_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">xavier_uniform_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gain</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L437"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.xavier_uniform_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input <cite>Tensor</cite> with values using a Xavier uniform distribution.</p>
 <p>The method is described in <cite>Understanding the difficulty of training
 deep feedforward neural networks</cite> - Glorot, X. &amp; Bengio, Y. (2010).
@@ -4686,7 +4686,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.xavier_normal_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">xavier_normal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gain</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.xavier_normal_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">xavier_normal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gain</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L470"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.xavier_normal_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input <cite>Tensor</cite> with values using a Xavier normal distribution.</p>
 <p>The method is described in <cite>Understanding the difficulty of training deep feedforward
 neural networks</cite> - Glorot, X. &amp; Bengio, Y. (2010). The resulting tensor
@@ -4723,7 +4723,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.kaiming_uniform_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">kaiming_uniform_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fan_in'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'leaky_relu'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L511"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.kaiming_uniform_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">kaiming_uniform_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fan_in'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'leaky_relu'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L511"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.kaiming_uniform_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input <cite>Tensor</cite> with values using a Kaiming uniform distribution.</p>
 <p>The method is described in <cite>Delving deep into rectifiers: Surpassing
 human-level performance on ImageNet classification</cite> - He, K. et al. (2015).
@@ -4777,7 +4777,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.kaiming_normal_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">kaiming_normal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fan_in'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'leaky_relu'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L576"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.kaiming_normal_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">kaiming_normal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fan_in'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">nonlinearity</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'leaky_relu'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L576"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.kaiming_normal_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input <cite>Tensor</cite> with values using a Kaiming normal distribution.</p>
 <p>The method is described in <cite>Delving deep into rectifiers: Surpassing
 human-level performance on ImageNet classification</cite> - He, K. et al. (2015).
@@ -4834,7 +4834,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.trunc_normal_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">trunc_normal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mean</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">std</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L267"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.trunc_normal_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">trunc_normal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mean</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">std</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">a</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">b</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">2.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L267"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.trunc_normal_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input Tensor with values drawn from a truncated normal distribution.</p>
 <p>The values are effectively drawn from the
 normal distribution <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="script">N</mi><mo stretchy="false">(</mo><mtext>mean</mtext><mo separator="true">,</mo><msup><mtext>std</mtext><mn>2</mn></msup><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\mathcal{N}(\text{mean}, \text{std}^2)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1.1484em;vertical-align:-0.25em;"></span><span class="mord mathcal" style="margin-right:0.14736em;">N</span><span class="mopen">(</span><span class="mord text"><span class="mord">mean</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord"><span class="mord text"><span class="mord">std</span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8984em;"><span style="top:-3.1473em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span>
@@ -4865,7 +4865,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.orthogonal_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">orthogonal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gain</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L629"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.orthogonal_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">orthogonal_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">gain</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L629"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.orthogonal_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the input <cite>Tensor</cite> with a (semi) orthogonal matrix.</p>
 <p>Described in <cite>Exact solutions to the nonlinear dynamics of learning in deep
 linear neural networks</cite> - Saxe, A. et al. (2013). The input tensor must have
@@ -4892,7 +4892,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.nn.init.sparse_">
-<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">sparse_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparsity</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">std</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/nn/init.py#L680"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.sparse_" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.nn.init.</span></span><span class="sig-name descname"><span class="pre">sparse_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sparsity</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">std</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.01</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">generator</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/nn/init.py#L680"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.nn.init.sparse_" title="Permalink to this definition">#</a></dt>
 <dd><p>Fill the 2D input <cite>Tensor</cite> as a sparse matrix.</p>
 <p>The non-zero elements will be drawn from the normal distribution
 <span class="math"><span class="katex"><span class="katex-mathml"><math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi mathvariant="script">N</mi><mo stretchy="false">(</mo><mn>0</mn><mo separator="true">,</mo><mn>0.01</mn><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">\mathcal{N}(0, 0.01)</annotation></semantics></math></span><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord mathcal" style="margin-right:0.14736em;">N</span><span class="mopen">(</span><span class="mord">0</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.1667em;"></span><span class="mord">0.01</span><span class="mclose">)</span></span></span></span></span>, as described in <cite>Deep learning via
diff --git a/2.9/notes/serialization.html b/2.9/notes/serialization.html
index 37ae3aaef16..d95585fba90 100644
--- a/2.9/notes/serialization.html
+++ b/2.9/notes/serialization.html
@@ -1984,7 +1984,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 <p>The following utility functions are related to serialization:</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.register_package">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">register_package</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">priority</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tagger</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">deserializer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L443"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.register_package" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">register_package</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">priority</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tagger</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">deserializer</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L443"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.register_package" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers callables for tagging and deserializing storage objects with an associated priority.
 Tagging associates a device with a storage object at save time while deserializing moves a
 storage object to an appropriate device at load time. <code class="xref py py-attr docutils literal notranslate"><span class="pre">tagger</span></code> and <code class="xref py py-attr docutils literal notranslate"><span class="pre">deserializer</span></code>
@@ -2025,7 +2025,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.get_crc32_options">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_crc32_options</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_crc32_options" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_crc32_options</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L171"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_crc32_options" title="Permalink to this definition">#</a></dt>
 <dd><p>Get whether <a class="reference internal" href="../generated/torch.save.html#torch.save" title="torch.save"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.save()</span></code></a> computes and writes crc32 for each record.</p>
 <p>Defaults to <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
 <dl class="field-list simple">
@@ -2037,7 +2037,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.set_crc32_options">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">set_crc32_options</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">compute_crc32</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L182"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.set_crc32_options" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">set_crc32_options</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">compute_crc32</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L182"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.set_crc32_options" title="Permalink to this definition">#</a></dt>
 <dd><p>Set whether <a class="reference internal" href="../generated/torch.save.html#torch.save" title="torch.save"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.save()</span></code></a> computes and writes crc32 for each record.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -2054,7 +2054,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.get_default_load_endianness">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_default_load_endianness</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_default_load_endianness" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_default_load_endianness</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L137"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_default_load_endianness" title="Permalink to this definition">#</a></dt>
 <dd><p>Get fallback byte order for loading files</p>
 <p>If byteorder mark is not present in saved checkpoint,
 this byte order is used as fallback.
@@ -2071,7 +2071,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.set_default_load_endianness">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">set_default_load_endianness</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">endianness</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.set_default_load_endianness" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">set_default_load_endianness</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">endianness</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.set_default_load_endianness" title="Permalink to this definition">#</a></dt>
 <dd><p>Set fallback byte order for loading files</p>
 <p>If byteorder mark is not present in saved checkpoint,
 this byte order is used as fallback.
@@ -2085,7 +2085,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.get_default_mmap_options">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_default_mmap_options</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_default_mmap_options" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_default_mmap_options</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L199"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_default_mmap_options" title="Permalink to this definition">#</a></dt>
 <dd><p>Get default mmap options for <a class="reference internal" href="../generated/torch.load.html#torch.load" title="torch.load"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.load()</span></code></a> with <code class="docutils literal notranslate"><span class="pre">mmap=True</span></code>.</p>
 <p>Defaults to <code class="docutils literal notranslate"><span class="pre">mmap.MAP_PRIVATE</span></code>.</p>
 <dl class="field-list simple">
@@ -2100,7 +2100,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.set_default_mmap_options">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">set_default_mmap_options</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flags</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L228"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.set_default_mmap_options" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">set_default_mmap_options</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">flags</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L228"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.set_default_mmap_options" title="Permalink to this definition">#</a></dt>
 <dd><p>Context manager or function to set default mmap options for <a class="reference internal" href="../generated/torch.load.html#torch.load" title="torch.load"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.load()</span></code></a> with <code class="docutils literal notranslate"><span class="pre">mmap=True</span></code> to flags.</p>
 <p>For now, only either <code class="docutils literal notranslate"><span class="pre">mmap.MAP_PRIVATE</span></code> or <code class="docutils literal notranslate"><span class="pre">mmap.MAP_SHARED</span></code> are supported.
 Please open an issue if you need any other option to be added here.</p>
@@ -2117,7 +2117,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.add_safe_globals">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">add_safe_globals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">safe_globals</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.add_safe_globals" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">add_safe_globals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">safe_globals</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L281"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.add_safe_globals" title="Permalink to this definition">#</a></dt>
 <dd><p>Marks the given globals as safe for <code class="docutils literal notranslate"><span class="pre">weights_only</span></code> load. For example, functions
 added to this list can be called during unpickling, classes could be instantiated
 and have state set.</p>
@@ -2152,7 +2152,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.clear_safe_globals">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">clear_safe_globals</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L267"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.clear_safe_globals" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">clear_safe_globals</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L267"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.clear_safe_globals" title="Permalink to this definition">#</a></dt>
 <dd><p>Clears the list of globals that are safe for <code class="docutils literal notranslate"><span class="pre">weights_only</span></code> load.</p>
 <dl class="field-list simple">
 </dl>
@@ -2160,7 +2160,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.get_safe_globals">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_safe_globals</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_safe_globals" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_safe_globals</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L274"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_safe_globals" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the list of user-added globals that are safe for <code class="docutils literal notranslate"><span class="pre">weights_only</span></code> load.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -2171,7 +2171,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.serialization.get_unsafe_globals_in_checkpoint">
-<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_unsafe_globals_in_checkpoint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_unsafe_globals_in_checkpoint" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">get_unsafe_globals_in_checkpoint</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.get_unsafe_globals_in_checkpoint" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a list of strings of functions/classes in a <code class="docutils literal notranslate"><span class="pre">torch.save</span></code> object that are not safe for <code class="docutils literal notranslate"><span class="pre">weights_only</span></code>.</p>
 <p>For a given function or class <code class="docutils literal notranslate"><span class="pre">f</span></code>, the corresponding string will be of the form
 <code class="docutils literal notranslate"><span class="pre">{f.__module__}.{f.__name__}</span></code>.</p>
@@ -2199,7 +2199,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.serialization.safe_globals">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">safe_globals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">safe_globals</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.safe_globals" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">safe_globals</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">safe_globals</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.safe_globals" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that adds certain globals as safe for <code class="docutils literal notranslate"><span class="pre">weights_only</span></code> load.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -2227,7 +2227,7 @@ <h4><a class="toc-backref" href="#id12">Environment Variables</a><a class="heade
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.serialization.skip_data">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">skip_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">materialize_fake_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/serialization.py#L384"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.skip_data" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.serialization.</span></span><span class="sig-name descname"><span class="pre">skip_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">materialize_fake_tensors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/serialization.py#L384"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.serialization.skip_data" title="Permalink to this definition">#</a></dt>
 <dd><p>Context-manager that skips writing/reading storage bytes for <code class="docutils literal notranslate"><span class="pre">torch.save</span></code> / <code class="docutils literal notranslate"><span class="pre">torch.load</span></code> calls.</p>
 <p>For the save path, storages will still be saved, but the space that their bytes would usually be written to
 will be empty space. The storage bytes can then be populated in a separate pass.</p>
diff --git a/2.9/onnx.html b/2.9/onnx.html
index 8d8a21aa44f..924b3e478aa 100644
--- a/2.9/onnx.html
+++ b/2.9/onnx.html
@@ -4459,7 +4459,7 @@ <h2>Contributing / Developing<a class="headerlink" href="#contributing-developin
 <h3>Functions<a class="headerlink" href="#functions" title="Permalink to this heading">#</a></h3>
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args=()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_names=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_names=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamo=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">external_data=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_translation_table=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">report=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verify=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dump_exported_program=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">artifacts_dir='.'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export_params=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_initializers_as_inputs=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_axes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training=&lt;TrainingMode.EVAL:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">operator_export_type=&lt;OperatorExportTypes.ONNX:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">do_constant_folding=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_opsets=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export_modules_as_functions=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autograd_inlining=True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/__init__.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args=()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_names=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_names=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamo=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">external_data=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_translation_table=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">report=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verify=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dump_exported_program=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">artifacts_dir='.'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export_params=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_initializers_as_inputs=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_axes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training=&lt;TrainingMode.EVAL:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">operator_export_type=&lt;OperatorExportTypes.ONNX:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">do_constant_folding=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_opsets=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export_modules_as_functions=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autograd_inlining=True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/__init__.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd><p>Exports a model into ONNX format.</p>
 <p>Setting <code class="docutils literal notranslate"><span class="pre">dynamo=True</span></code> enables the new ONNX export logic
 which is based on <a class="reference internal" href="export/api_reference.html#torch.export.ExportedProgram" title="torch.export.ExportedProgram"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.export.ExportedProgram</span></code></a> and a more modern
@@ -4656,7 +4656,7 @@ <h3>Functions<a class="headerlink" href="#functions" title="Permalink to this he
 
 <dl class="py function">
 <dt class="sig sig-object py">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">is_in_onnx_export</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/__init__.py#L365"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">is_in_onnx_export</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/__init__.py#L365"><span class="viewcode-link"><span class="pre">[source]</span></span></a></dt>
 <dd><p>Returns whether it is in the middle of ONNX export.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4698,7 +4698,7 @@ <h3>Deprecated APIs<a class="headerlink" href="#deprecated-apis" title="Permalin
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.register_custom_op_symbolic">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">register_custom_op_symbolic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbolic_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">symbolic_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/torchscript_exporter/utils.py#L1835"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.register_custom_op_symbolic" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">register_custom_op_symbolic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbolic_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">symbolic_fn</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/torchscript_exporter/utils.py#L1835"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.register_custom_op_symbolic" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a symbolic function for a custom operator.</p>
 <p>When the user registers symbolic for custom/contrib ops,
 it is highly recommended to add shape inference for that operator via setType API,
@@ -4721,7 +4721,7 @@ <h3>Deprecated APIs<a class="headerlink" href="#deprecated-apis" title="Permalin
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.unregister_custom_op_symbolic">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">unregister_custom_op_symbolic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbolic_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/torchscript_exporter/utils.py#L1865"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.unregister_custom_op_symbolic" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">unregister_custom_op_symbolic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">symbolic_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/torchscript_exporter/utils.py#L1865"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.unregister_custom_op_symbolic" title="Permalink to this definition">#</a></dt>
 <dd><p>Unregisters <code class="docutils literal notranslate"><span class="pre">symbolic_name</span></code>.</p>
 <p>See “Custom Operators” in the module documentation for an example usage.</p>
 <dl class="field-list simple">
@@ -4737,7 +4737,7 @@ <h3>Deprecated APIs<a class="headerlink" href="#deprecated-apis" title="Permalin
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.select_model_mode_for_export">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">select_model_mode_for_export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/torchscript_exporter/utils.py#L91"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.select_model_mode_for_export" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">select_model_mode_for_export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mode</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/torchscript_exporter/utils.py#L91"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.select_model_mode_for_export" title="Permalink to this definition">#</a></dt>
 <dd><p>A context manager to temporarily set the training mode of <code class="docutils literal notranslate"><span class="pre">model</span></code>
 to <code class="docutils literal notranslate"><span class="pre">mode</span></code>, resetting it when we exit the with-block.</p>
 <div class="deprecated">
diff --git a/2.9/onnx_export.html b/2.9/onnx_export.html
index 700af9a9564..5c6ef738022 100644
--- a/2.9/onnx_export.html
+++ b/2.9/onnx_export.html
@@ -4618,7 +4618,7 @@ <h2><a class="toc-backref" href="#id6">Metadata</a><a class="headerlink" href="#
 <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" href="#api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.export">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args=()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_names=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_names=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamo=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">external_data=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_translation_table=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">report=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verify=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dump_exported_program=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">artifacts_dir='.'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export_params=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_initializers_as_inputs=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_axes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training=&lt;TrainingMode.EVAL:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">operator_export_type=&lt;OperatorExportTypes.ONNX:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">do_constant_folding=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_opsets=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export_modules_as_functions=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autograd_inlining=True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/__init__.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.export" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args=()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">f=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_names=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_names=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">opset_version=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamo=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">external_data=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_shapes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_translation_table=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">report=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">optimize=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verify=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dump_exported_program=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">artifacts_dir='.'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fallback=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export_params=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_initializers_as_inputs=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dynamic_axes=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">training=&lt;TrainingMode.EVAL:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">operator_export_type=&lt;OperatorExportTypes.ONNX:</span> <span class="pre">0&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">do_constant_folding=True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_opsets=None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">export_modules_as_functions=False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">autograd_inlining=True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/__init__.py#L59"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.export" title="Permalink to this definition">#</a></dt>
 <dd><p>Exports a model into ONNX format.</p>
 <p>Setting <code class="docutils literal notranslate"><span class="pre">dynamo=True</span></code> enables the new ONNX export logic
 which is based on <a class="reference internal" href="export/api_reference.html#torch.export.ExportedProgram" title="torch.export.ExportedProgram"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.export.ExportedProgram</span></code></a> and a more modern
@@ -4827,7 +4827,7 @@ <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" hr
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.ONNXProgram.apply_weights">
-<span class="sig-name descname"><span class="pre">apply_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_onnx_program.py#L388"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.apply_weights" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">apply_weights</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_dict</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_onnx_program.py#L388"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.apply_weights" title="Permalink to this definition">#</a></dt>
 <dd><p>Apply the weights from the specified state dict to the ONNX model.</p>
 <p>Use this method to replace FakeTensors or other weights.</p>
 <dl class="field-list simple">
@@ -4839,7 +4839,7 @@ <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.ONNXProgram.call_reference">
-<span class="sig-name descname"><span class="pre">call_reference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_onnx_program.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.call_reference" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">call_reference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_onnx_program.py#L261"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.call_reference" title="Permalink to this definition">#</a></dt>
 <dd><p>Run the ONNX model using the reference backend.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -4850,7 +4850,7 @@ <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.ONNXProgram.compute_values">
-<span class="sig-name descname"><span class="pre">compute_values</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value_names</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_onnx_program.py#L276"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.compute_values" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">compute_values</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value_names</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_onnx_program.py#L276"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.compute_values" title="Permalink to this definition">#</a></dt>
 <dd><p>Compute the values of the specified names in the ONNX model.</p>
 <p>This method is used to compute the values of the specified names in the ONNX model.
 The values are returned as a dictionary mapping names to tensors.</p>
@@ -4869,7 +4869,7 @@ <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.ONNXProgram.initialize_inference_session">
-<span class="sig-name descname"><span class="pre">initialize_inference_session</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">initializer=&lt;function</span> <span class="pre">_ort_session_initializer&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_onnx_program.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.initialize_inference_session" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">initialize_inference_session</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">initializer=&lt;function</span> <span class="pre">_ort_session_initializer&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_onnx_program.py#L410"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.initialize_inference_session" title="Permalink to this definition">#</a></dt>
 <dd><p>Initialize the ONNX Runtime inference session.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4888,7 +4888,7 @@ <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.ONNXProgram.optimize">
-<span class="sig-name descname"><span class="pre">optimize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_onnx_program.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.optimize" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">optimize</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_onnx_program.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.optimize" title="Permalink to this definition">#</a></dt>
 <dd><p>Optimize the ONNX model.</p>
 <p>This method optimizes the ONNX model by performing constant folding and
 eliminating redundancies in the graph. The optimization is done in-place.</p>
@@ -4898,7 +4898,7 @@ <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.ONNXProgram.release">
-<span class="sig-name descname"><span class="pre">release</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_onnx_program.py#L440"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.release" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">release</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_onnx_program.py#L440"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.release" title="Permalink to this definition">#</a></dt>
 <dd><p>Release the inference session.</p>
 <p>You may call this method to release the resources used by the inference session.</p>
 <dl class="field-list simple">
@@ -4907,7 +4907,7 @@ <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" hr
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.ONNXProgram.save">
-<span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">destination</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_initializers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_initializers_as_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">external_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_onnx_program.py#L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.save" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">destination</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include_initializers</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_initializers_as_inputs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">external_data</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_onnx_program.py#L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ONNXProgram.save" title="Permalink to this definition">#</a></dt>
 <dd><p>Save the ONNX model to the specified destination.</p>
 <p>When <code class="docutils literal notranslate"><span class="pre">external_data</span></code> is <code class="docutils literal notranslate"><span class="pre">True</span></code> or the model is larger than 2GB,
 the weights are saved as external data in a separate file.</p>
@@ -4949,7 +4949,7 @@ <h2><a class="toc-backref" href="#id7">API Reference</a><a class="headerlink" hr
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.is_in_onnx_export">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">is_in_onnx_export</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/__init__.py#L365"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.is_in_onnx_export" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.</span></span><span class="sig-name descname"><span class="pre">is_in_onnx_export</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/__init__.py#L365"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.is_in_onnx_export" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns whether it is in the middle of ONNX export.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/onnx_ops.html b/2.9/onnx_ops.html
index b886991108b..7fb74fa1404 100644
--- a/2.9/onnx_ops.html
+++ b/2.9/onnx_ops.html
@@ -4413,7 +4413,7 @@ <h2>Symbolic Operators<a class="headerlink" href="#symbolic-operators" title="Pe
 inside an <code class="docutils literal notranslate"><span class="pre">if</span> <span class="pre">torch.onnx.is_in_onnx_export</span></code> block.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.ops.symbolic">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">symbolic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">domain_op</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attrs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata_props</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/ops/__init__.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.symbolic" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">symbolic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">domain_op</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attrs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata_props</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/ops/__init__.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.symbolic" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a symbolic FX operator to represent an arbitrary ONNX operator.</p>
 <p>This function is used to create a symbolic operator with a single output.
 To create an operator with multiple outputs, use <a class="reference internal" href="#torch.onnx.ops.symbolic_multi_out" title="torch.onnx.ops.symbolic_multi_out"><code class="xref py py-func docutils literal notranslate"><span class="pre">symbolic_multi_out()</span></code></a>.</p>
@@ -4473,7 +4473,7 @@ <h2>Symbolic Operators<a class="headerlink" href="#symbolic-operators" title="Pe
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.ops.symbolic_multi_out">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">symbolic_multi_out</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">domain_op</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attrs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtypes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shapes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata_props</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/ops/__init__.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.symbolic_multi_out" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">symbolic_multi_out</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">domain_op</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">/</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inputs</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attrs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtypes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shapes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">version</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata_props</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/ops/__init__.py#L175"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.symbolic_multi_out" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a symbolic FX operator to represent an arbitrary ONNX operator with multiple outputs.</p>
 <p>You may use <code class="docutils literal notranslate"><span class="pre">if</span> <span class="pre">torch.onnx.is_in_onnx_export()</span></code> to conditionally enable the
 symbolic logic only during <code class="docutils literal notranslate"><span class="pre">torch.onnx.export()</span></code>.</p>
@@ -4599,7 +4599,7 @@ <h2>ONNX Operators<a class="headerlink" href="#onnx-operators" title="Permalink
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.ops.rotary_embedding">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">rotary_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cos_cache</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sin_cache</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">position_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">interleaved</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_heads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rotary_embedding_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/ops/__init__.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.rotary_embedding" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">rotary_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">X</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cos_cache</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sin_cache</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">position_ids</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">interleaved</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_heads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rotary_embedding_dim</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/ops/__init__.py#L283"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.rotary_embedding" title="Permalink to this definition">#</a></dt>
 <dd><p>RotaryEmbedding op in ONNX.</p>
 <p><a class="reference external" href="https://onnx.ai/onnx/operators/onnx__RotaryEmbedding.html">https://onnx.ai/onnx/operators/onnx__RotaryEmbedding.html</a></p>
 <p>RotaryEmbedding is the implementation of rotary positional embeddings (RoPE) based on the paper <a class="reference external" href="https://arxiv.org/pdf/2104.09864">https://arxiv.org/pdf/2104.09864</a>.
@@ -4652,7 +4652,7 @@ <h2>ONNX Operators<a class="headerlink" href="#onnx-operators" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.ops.attention">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">Q</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">K</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">V</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">past_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">past_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_num_heads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q_num_heads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qk_matmul_output_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">softcap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">softmax_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/ops/__init__.py#L349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.attention" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">attention</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">Q</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">K</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">V</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attn_mask</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">past_key</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">past_value</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_causal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kv_num_heads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">q_num_heads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">qk_matmul_output_mode</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scale</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">softcap</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">softmax_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/ops/__init__.py#L349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.attention" title="Permalink to this definition">#</a></dt>
 <dd><p>Attention op in ONNX.</p>
 <p><a class="reference external" href="https://onnx.ai/onnx/operators/onnx__Attention.html">https://onnx.ai/onnx/operators/onnx__Attention.html</a></p>
 <p>Computes scaled dot product attention on query, key and value tensors, using an optional attention mask if passed.</p>
@@ -4774,7 +4774,7 @@ <h2>ONNX to ATen Decomposition Table<a class="headerlink" href="#onnx-to-aten-de
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.ops.aten_decompositions">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">aten_decompositions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/ops/__init__.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.aten_decompositions" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.ops.</span></span><span class="sig-name descname"><span class="pre">aten_decompositions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/ops/__init__.py#L58"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.ops.aten_decompositions" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the ONNX to ATen decomp table.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
diff --git a/2.9/onnx_verification.html b/2.9/onnx_verification.html
index 0f56861417e..873d5a6592f 100644
--- a/2.9/onnx_verification.html
+++ b/2.9/onnx_verification.html
@@ -4406,7 +4406,7 @@
 <p>A set of tools to verify the correctness of ONNX models.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.onnx.verification.verify_onnx_program">
-<span class="sig-prename descclassname"><span class="pre">torch.onnx.verification.</span></span><span class="sig-name descname"><span class="pre">verify_onnx_program</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">onnx_program</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compare_intermediates</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_verification.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.verification.verify_onnx_program" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.onnx.verification.</span></span><span class="sig-name descname"><span class="pre">verify_onnx_program</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">onnx_program</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compare_intermediates</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_verification.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.verification.verify_onnx_program" title="Permalink to this definition">#</a></dt>
 <dd><p>Verify the ONNX model by comparing the values with the expected values from ExportedProgram.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4453,7 +4453,7 @@
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.verification.VerificationInfo.asdict">
-<span class="sig-name descname"><span class="pre">asdict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_verification.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.verification.VerificationInfo.asdict" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">asdict</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_verification.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.verification.VerificationInfo.asdict" title="Permalink to this definition">#</a></dt>
 <dd><p>Convert the VerificationInfo object to a dictionary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4467,7 +4467,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.onnx.verification.VerificationInfo.from_tensors">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">actual</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/onnx/_internal/exporter/_verification.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.verification.VerificationInfo.from_tensors" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_tensors</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">actual</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/onnx/_internal/exporter/_verification.py#L60"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.onnx.verification.VerificationInfo.from_tensors" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a VerificationInfo object from two tensors.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/optim.html b/2.9/optim.html
index 7ea8f596e03..85210cd665c 100644
--- a/2.9/optim.html
+++ b/2.9/optim.html
@@ -4510,7 +4510,7 @@ <h4><code class="docutils literal notranslate"><span class="pre">optimizer.step(
 <span id="optimizer-algorithms"></span><h2>Base class<a class="headerlink" href="#base-class" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.optim.Optimizer">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Optimizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">defaults</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/optimizer.py#L339"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.optim.</span></span><span class="sig-name descname"><span class="pre">Optimizer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">defaults</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/optimizer.py#L339"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.Optimizer" title="Permalink to this definition">#</a></dt>
 <dd><p>Base class for all optimizers.</p>
 <div class="admonition warning">
 <p class="admonition-title">Warning</p>
@@ -5272,13 +5272,13 @@ <h3>Putting it all together: EMA<a class="headerlink" href="#putting-it-all-toge
 </div>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.get_ema_multi_avg_fn">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.swa_utils.</span></span><span class="sig-name descname"><span class="pre">get_ema_multi_avg_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.999</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/swa_utils.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.get_ema_multi_avg_fn" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.swa_utils.</span></span><span class="sig-name descname"><span class="pre">get_ema_multi_avg_fn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decay</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.999</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/swa_utils.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.get_ema_multi_avg_fn" title="Permalink to this definition">#</a></dt>
 <dd><p>Get the function applying exponential moving average (EMA) across multiple params.</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.optim.swa_utils.update_bn">
-<span class="sig-prename descclassname"><span class="pre">torch.optim.swa_utils.</span></span><span class="sig-name descname"><span class="pre">update_bn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loader</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/optim/swa_utils.py#L315"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.update_bn" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.optim.swa_utils.</span></span><span class="sig-name descname"><span class="pre">update_bn</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">loader</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/optim/swa_utils.py#L315"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.optim.swa_utils.update_bn" title="Permalink to this definition">#</a></dt>
 <dd><p>Update BatchNorm running_mean, running_var buffers in the model.</p>
 <p>It performs one pass over data in <cite>loader</cite> to estimate the activation
 statistics for BatchNorm layers in the model.</p>
diff --git a/2.9/package.html b/2.9/package.html
index 835b51265ce..aae708e3e62 100644
--- a/2.9/package.html
+++ b/2.9/package.html
@@ -5071,7 +5071,7 @@ <h4>Mangling<a class="headerlink" href="#mangling" title="Permalink to this head
 <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" href="#api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.package.PackagingError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">PackagingError</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dependency_graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackagingError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">PackagingError</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dependency_graph</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackagingError" title="Permalink to this definition">#</a></dt>
 <dd><p>This exception is raised when there is an issue with exporting a package.
 <code class="docutils literal notranslate"><span class="pre">PackageExporter</span></code> will attempt to gather up all the errors and present
 them to you at once.</p>
@@ -5081,14 +5081,14 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.package.EmptyMatchError">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">EmptyMatchError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.EmptyMatchError" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">EmptyMatchError</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.EmptyMatchError" title="Permalink to this definition">#</a></dt>
 <dd><p>This is an exception that is thrown when a mock or extern is marked as
 <code class="docutils literal notranslate"><span class="pre">allow_empty=False</span></code>, and is not matched with any module during packaging.</p>
 </dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.package.PackageExporter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">PackageExporter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importer=&lt;torch.package.importer._SysImporter</span> <span class="pre">object&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">PackageExporter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importer=&lt;torch.package.importer._SysImporter</span> <span class="pre">object&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter" title="Permalink to this definition">#</a></dt>
 <dd><p>Exporters allow you to write packages of code, pickled Python data, and
 arbitrary binary and text resources into a self-contained package.</p>
 <p>Imports can load this code in a hermetic way, such that code is loaded
@@ -5112,7 +5112,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.__init__">
-<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importer=&lt;torch.package.importer._SysImporter</span> <span class="pre">object&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.__init__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">importer=&lt;torch.package.importer._SysImporter</span> <span class="pre">object&gt;</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">debug=False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.__init__" title="Permalink to this definition">#</a></dt>
 <dd><p>Create an exporter.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5129,7 +5129,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.add_dependency">
-<span class="sig-name descname"><span class="pre">add_dependency</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.add_dependency" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_dependency</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L452"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.add_dependency" title="Permalink to this definition">#</a></dt>
 <dd><p>Given a module, add it to the dependency graph according to patterns
 specified by the user.</p>
 <dl class="field-list simple">
@@ -5138,7 +5138,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.all_paths">
-<span class="sig-name descname"><span class="pre">all_paths</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L1164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.all_paths" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">all_paths</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dst</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L1164"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.all_paths" title="Permalink to this definition">#</a></dt>
 <dd><dl class="simple">
 <dt>Return a dot representation of the subgraph</dt><dd><p>that has all paths from src to dst.</p>
 </dd>
@@ -5156,7 +5156,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.close">
-<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.close" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.close" title="Permalink to this definition">#</a></dt>
 <dd><p>Write the package to the filesystem. Any calls after <a class="reference internal" href="#torch.package.PackageExporter.close" title="torch.package.PackageExporter.close"><code class="xref py py-meth docutils literal notranslate"><span class="pre">close()</span></code></a> are now invalid.
 It is preferable to use resource guard syntax instead:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">with</span> <span class="n">PackageExporter</span><span class="p">(</span><span class="s2">&quot;file.zip&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
@@ -5167,7 +5167,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.denied_modules">
-<span class="sig-name descname"><span class="pre">denied_modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L1144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.denied_modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">denied_modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L1144"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.denied_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return all modules that are currently denied.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5182,7 +5182,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.deny">
-<span class="sig-name descname"><span class="pre">deny</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">include</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L890"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.deny" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">deny</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">include</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L890"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.deny" title="Permalink to this definition">#</a></dt>
 <dd><p>Blocklist modules who names match the given glob patterns from the list of modules the package can import.
 If a dependency on any matching packages is found, a <a class="reference internal" href="#torch.package.PackagingError" title="torch.package.PackagingError"><code class="xref py py-class docutils literal notranslate"><span class="pre">PackagingError</span></code></a> is raised.</p>
 <dl class="field-list simple">
@@ -5198,7 +5198,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.dependency_graph_string">
-<span class="sig-name descname"><span class="pre">dependency_graph_string</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L1098"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.dependency_graph_string" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">dependency_graph_string</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L1098"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.dependency_graph_string" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns digraph string representation of dependencies in package.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5212,7 +5212,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.extern">
-<span class="sig-name descname"><span class="pre">extern</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">include</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_empty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L859"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.extern" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">extern</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">include</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_empty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L859"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.extern" title="Permalink to this definition">#</a></dt>
 <dd><p>Include <code class="docutils literal notranslate"><span class="pre">module</span></code> in the list of external modules the package can import.
 This will prevent dependency discovery from saving
 it in the package. The importer will load an external module directly from the standard import system.
@@ -5237,7 +5237,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.externed_modules">
-<span class="sig-name descname"><span class="pre">externed_modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L1117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.externed_modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">externed_modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L1117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.externed_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return all modules that are currently externed.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5252,7 +5252,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.get_rdeps">
-<span class="sig-name descname"><span class="pre">get_rdeps</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L1153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.get_rdeps" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_rdeps</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L1153"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.get_rdeps" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a list of all modules which depend on the module <code class="docutils literal notranslate"><span class="pre">module_name</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5266,7 +5266,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.get_unique_id">
-<span class="sig-name descname"><span class="pre">get_unique_id</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.get_unique_id" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_unique_id</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.get_unique_id" title="Permalink to this definition">#</a></dt>
 <dd><p>Get an id. This id is guaranteed to only be handed out once for this package.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5277,7 +5277,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.intern">
-<span class="sig-name descname"><span class="pre">intern</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">include</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_empty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L792"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.intern" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">intern</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">include</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_empty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L792"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.intern" title="Permalink to this definition">#</a></dt>
 <dd><p>Specify modules that should be packaged. A module must match some <code class="docutils literal notranslate"><span class="pre">intern</span></code> pattern in order to be
 included in the package and have its dependencies processed recursively.</p>
 <dl class="field-list simple">
@@ -5297,7 +5297,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.interned_modules">
-<span class="sig-name descname"><span class="pre">interned_modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L1126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.interned_modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">interned_modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L1126"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.interned_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return all modules that are currently interned.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5312,7 +5312,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.mock">
-<span class="sig-name descname"><span class="pre">mock</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">include</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_empty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L818"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.mock" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mock</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">include</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_empty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L818"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.mock" title="Permalink to this definition">#</a></dt>
 <dd><p>Replace some required modules with a mock implementation.  Mocked modules will return a fake
 object for any attribute accessed from it. Because we copy file-by-file, the dependency resolution will sometimes
 find files that are imported by model files but whose functionality is never used
@@ -5348,7 +5348,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.mocked_modules">
-<span class="sig-name descname"><span class="pre">mocked_modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L1135"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.mocked_modules" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mocked_modules</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L1135"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.mocked_modules" title="Permalink to this definition">#</a></dt>
 <dd><p>Return all modules that are currently mocked.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -5363,7 +5363,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.register_extern_hook">
-<span class="sig-name descname"><span class="pre">register_extern_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L735"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.register_extern_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_extern_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L735"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.register_extern_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers an extern hook on the exporter.</p>
 <p>The hook will be called each time a module matches against an <a class="reference internal" href="#torch.package.PackageExporter.extern" title="torch.package.PackageExporter.extern"><code class="xref py py-meth docutils literal notranslate"><span class="pre">extern()</span></code></a> pattern.
 It should have the following signature:</p>
@@ -5384,7 +5384,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.register_intern_hook">
-<span class="sig-name descname"><span class="pre">register_intern_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L773"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.register_intern_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_intern_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L773"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.register_intern_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers an intern hook on the exporter.</p>
 <p>The hook will be called each time a module matches against an <a class="reference internal" href="#torch.package.PackageExporter.intern" title="torch.package.PackageExporter.intern"><code class="xref py py-meth docutils literal notranslate"><span class="pre">intern()</span></code></a> pattern.
 It should have the following signature:</p>
@@ -5405,7 +5405,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.register_mock_hook">
-<span class="sig-name descname"><span class="pre">register_mock_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.register_mock_hook" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">register_mock_hook</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hook</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.register_mock_hook" title="Permalink to this definition">#</a></dt>
 <dd><p>Registers a mock hook on the exporter.</p>
 <p>The hook will be called each time a module matches against a <a class="reference internal" href="#torch.package.PackageExporter.mock" title="torch.package.PackageExporter.mock"><code class="xref py py-meth docutils literal notranslate"><span class="pre">mock()</span></code></a> pattern.
 It should have the following signature:</p>
@@ -5426,7 +5426,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.save_binary">
-<span class="sig-name descname"><span class="pre">save_binary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">binary</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_binary" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_binary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">binary</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_binary" title="Permalink to this definition">#</a></dt>
 <dd><p>Save raw bytes to the package.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5441,7 +5441,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.save_module">
-<span class="sig-name descname"><span class="pre">save_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L511"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L511"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Save the code for <code class="docutils literal notranslate"><span class="pre">module</span></code> into the package. Code for the module is resolved using the <code class="docutils literal notranslate"><span class="pre">importers</span></code> path to find the
 module object, and then using its <code class="docutils literal notranslate"><span class="pre">__file__</span></code> attribute to find the source code.</p>
 <dl class="field-list simple">
@@ -5457,7 +5457,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.save_pickle">
-<span class="sig-name descname"><span class="pre">save_pickle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_pickle" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_pickle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L583"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_pickle" title="Permalink to this definition">#</a></dt>
 <dd><p>Save a python object to the archive using pickle. Equivalent to <a class="reference internal" href="generated/torch.save.html#torch.save" title="torch.save"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.save()</span></code></a> but saving into
 the archive rather than a stand-alone file. Standard pickle does not save the code, only the objects.
 If <code class="docutils literal notranslate"><span class="pre">dependencies</span></code> is true, this method will also scan the pickled objects for which modules are required
@@ -5480,7 +5480,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.save_source_file">
-<span class="sig-name descname"><span class="pre">save_source_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_or_directory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L262"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_source_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_source_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_or_directory</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L262"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_source_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Adds the local file system <code class="docutils literal notranslate"><span class="pre">file_or_directory</span></code> to the source package to provide the code
 for <code class="docutils literal notranslate"><span class="pre">module_name</span></code>.</p>
 <dl class="field-list simple">
@@ -5498,7 +5498,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.save_source_string">
-<span class="sig-name descname"><span class="pre">save_source_string</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_package</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L371"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_source_string" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_source_string</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">module_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">src</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_package</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dependencies</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L371"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_source_string" title="Permalink to this definition">#</a></dt>
 <dd><p>Adds <code class="docutils literal notranslate"><span class="pre">src</span></code> as the source code for <code class="docutils literal notranslate"><span class="pre">module_name</span></code> in the exported package.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5515,7 +5515,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageExporter.save_text">
-<span class="sig-name descname"><span class="pre">save_text</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">text</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_exporter.py#L714"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_text" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">save_text</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">text</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_exporter.py#L714"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageExporter.save_text" title="Permalink to this definition">#</a></dt>
 <dd><p>Save text data to the package.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5532,7 +5532,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.package.PackageImporter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">PackageImporter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_or_buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_allowed=&lt;function</span> <span class="pre">PackageImporter.&lt;lambda&gt;&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L66"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">PackageImporter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_or_buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_allowed=&lt;function</span> <span class="pre">PackageImporter.&lt;lambda&gt;&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L66"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter" title="Permalink to this definition">#</a></dt>
 <dd><p>Importers allow you to load code written to packages by <a class="reference internal" href="#torch.package.PackageExporter" title="torch.package.PackageExporter"><code class="xref py py-class docutils literal notranslate"><span class="pre">PackageExporter</span></code></a>.
 Code is loaded in a hermetic way, using files from the package
 rather than the normal python import system. This allows
@@ -5547,7 +5547,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageImporter.__init__">
-<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_or_buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_allowed=&lt;function</span> <span class="pre">PackageImporter.&lt;lambda&gt;&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.__init__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_or_buffer</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">module_allowed=&lt;function</span> <span class="pre">PackageImporter.&lt;lambda&gt;&gt;</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L86"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.__init__" title="Permalink to this definition">#</a></dt>
 <dd><p>Open <code class="docutils literal notranslate"><span class="pre">file_or_buffer</span></code> for importing. This checks that the imported package only requires modules
 allowed by <code class="docutils literal notranslate"><span class="pre">module_allowed</span></code></p>
 <dl class="field-list simple">
@@ -5568,7 +5568,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageImporter.file_structure">
-<span class="sig-name descname"><span class="pre">file_structure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'**'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L322"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.file_structure" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">file_structure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">include</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'**'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">()</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L322"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.file_structure" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a file structure representation of package’s zipfile.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5590,7 +5590,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageImporter.id">
-<span class="sig-name descname"><span class="pre">id</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.id" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">id</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.id" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns internal identifier that torch.package uses to distinguish <a class="reference internal" href="#torch.package.PackageImporter" title="torch.package.PackageImporter"><code class="xref py py-class docutils literal notranslate"><span class="pre">PackageImporter</span></code></a> instances.
 Looks like:</p>
 <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="o">&lt;</span><span class="n">torch_package_0</span><span class="o">&gt;</span>
@@ -5600,7 +5600,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageImporter.import_module">
-<span class="sig-name descname"><span class="pre">import_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">package</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.import_module" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">import_module</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">package</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L157"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.import_module" title="Permalink to this definition">#</a></dt>
 <dd><p>Load a module from the package if it hasn’t already been loaded, and then return
 the module. Modules are loaded locally
 to the importer and will appear in <code class="docutils literal notranslate"><span class="pre">self.modules</span></code> rather than <code class="docutils literal notranslate"><span class="pre">sys.modules</span></code>.</p>
@@ -5622,7 +5622,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageImporter.load_binary">
-<span class="sig-name descname"><span class="pre">load_binary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L180"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.load_binary" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_binary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L180"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.load_binary" title="Permalink to this definition">#</a></dt>
 <dd><p>Load raw bytes.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5642,7 +5642,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageImporter.load_pickle">
-<span class="sig-name descname"><span class="pre">load_pickle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L215"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.load_pickle" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_pickle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">map_location</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L215"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.load_pickle" title="Permalink to this definition">#</a></dt>
 <dd><p>Unpickles the resource from the package, loading any modules that are needed to construct the objects
 using <a class="reference internal" href="#torch.package.PackageImporter.import_module" title="torch.package.PackageImporter.import_module"><code class="xref py py-meth docutils literal notranslate"><span class="pre">import_module()</span></code></a>.</p>
 <dl class="field-list simple">
@@ -5664,7 +5664,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageImporter.load_text">
-<span class="sig-name descname"><span class="pre">load_text</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'utf-8'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">errors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'strict'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.load_text" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">load_text</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">package</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">resource</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoding</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'utf-8'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">errors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'strict'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L194"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.load_text" title="Permalink to this definition">#</a></dt>
 <dd><p>Load a string.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5686,7 +5686,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.PackageImporter.python_version">
-<span class="sig-name descname"><span class="pre">python_version</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/package_importer.py#L341"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.python_version" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">python_version</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/package_importer.py#L341"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.PackageImporter.python_version" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the version of python that was used to create this package.</p>
 <p>Note: this function is experimental and not Forward Compatible. The plan is to move this into a lock
 file later on.</p>
@@ -5701,7 +5701,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.package.Directory">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">Directory</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dir</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/file_structure_representation.py#L9"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.Directory" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.package.</span></span><span class="sig-name descname"><span class="pre">Directory</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_dir</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/file_structure_representation.py#L9"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.Directory" title="Permalink to this definition">#</a></dt>
 <dd><p>A file structure representation. Organized as Directory nodes that have lists of
 their Directory children. Directories for a package are created by calling
 <a class="reference internal" href="#torch.package.PackageImporter.file_structure" title="torch.package.PackageImporter.file_structure"><code class="xref py py-meth docutils literal notranslate"><span class="pre">PackageImporter.file_structure()</span></code></a>.</p>
@@ -5709,7 +5709,7 @@ <h2><a class="toc-backref" href="#id19">API Reference</a><a class="headerlink" h
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.package.Directory.has_file">
-<span class="sig-name descname"><span class="pre">has_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/package/file_structure_representation.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.Directory.has_file" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">has_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/package/file_structure_representation.py#L47"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.package.Directory.has_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Checks if a file is present in a <a class="reference internal" href="#torch.package.Directory" title="torch.package.Directory"><code class="xref py py-class docutils literal notranslate"><span class="pre">Directory</span></code></a>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/profiler.html b/2.9/profiler.html
index 18a2cdfd020..9184ce5a9f6 100644
--- a/2.9/profiler.html
+++ b/2.9/profiler.html
@@ -4408,7 +4408,7 @@ <h1>torch.profiler<a class="headerlink" href="#torch-profiler" title="Permalink
 <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">_KinetoProfile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activities</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_stack</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_flops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">experimental_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">execution_trace_observer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">acc_events</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_trace_id_callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L95"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">_KinetoProfile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activities</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_stack</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_flops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">experimental_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">execution_trace_observer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">acc_events</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_trace_id_callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L95"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile" title="Permalink to this definition">#</a></dt>
 <dd><p>Low-level profiler wrap the autograd profile</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4451,7 +4451,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 </div>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.add_metadata">
-<span class="sig-name descname"><span class="pre">add_metadata</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L344"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.add_metadata" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_metadata</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L344"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.add_metadata" title="Permalink to this definition">#</a></dt>
 <dd><p>Adds a user defined metadata with a string key and a string value
 into the trace file</p>
 <dl class="field-list simple">
@@ -4460,7 +4460,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.add_metadata_json">
-<span class="sig-name descname"><span class="pre">add_metadata_json</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L352"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.add_metadata_json" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_metadata_json</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L352"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.add_metadata_json" title="Permalink to this definition">#</a></dt>
 <dd><p>Adds a user defined metadata with a string key and a valid json value
 into the trace file</p>
 <dl class="field-list simple">
@@ -4469,14 +4469,14 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.events">
-<span class="sig-name descname"><span class="pre">events</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L336"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.events" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">events</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L336"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.events" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the list of unaggregated profiler events,
 to be used in the trace callback or after the profiling is finished</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.export_chrome_trace">
-<span class="sig-name descname"><span class="pre">export_chrome_trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.export_chrome_trace" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">export_chrome_trace</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.export_chrome_trace" title="Permalink to this definition">#</a></dt>
 <dd><p>Exports the collected trace in Chrome JSON format. If kineto is enabled, only
 last cycle in schedule is exported.</p>
 <dl class="field-list simple">
@@ -4485,7 +4485,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.export_memory_timeline">
-<span class="sig-name descname"><span class="pre">export_memory_timeline</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.export_memory_timeline" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">export_memory_timeline</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L395"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.export_memory_timeline" title="Permalink to this definition">#</a></dt>
 <dd><p>Export memory event information from the profiler collected
 tree for a given device, and export a timeline plot. There are 3
 exportable files using <code class="docutils literal notranslate"><span class="pre">export_memory_timeline</span></code>, each controlled by the
@@ -4510,7 +4510,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.export_stacks">
-<span class="sig-name descname"><span class="pre">export_stacks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metric</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'self_cpu_time_total'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.export_stacks" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">export_stacks</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metric</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'self_cpu_time_total'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.export_stacks" title="Permalink to this definition">#</a></dt>
 <dd><p>Save stack traces to a file</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4524,7 +4524,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.key_averages">
-<span class="sig-name descname"><span class="pre">key_averages</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group_by_input_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_by_stack_n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_by_overload_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.key_averages" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">key_averages</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">group_by_input_shape</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_by_stack_n</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">group_by_overload_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L318"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.key_averages" title="Permalink to this definition">#</a></dt>
 <dd><p>Averages events, grouping them by operator name and (optionally) input shapes, stack
 and overload name.</p>
 <div class="admonition note">
@@ -4538,7 +4538,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.preset_metadata_json">
-<span class="sig-name descname"><span class="pre">preset_metadata_json</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L359"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.preset_metadata_json" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">preset_metadata_json</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L359"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.preset_metadata_json" title="Permalink to this definition">#</a></dt>
 <dd><p>Preset a user defined metadata when the profiler is not started
 and added into the trace file later.
 Metadata is in the format of a string key and a valid json value</p>
@@ -4548,7 +4548,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler._KinetoProfile.toggle_collection_dynamic">
-<span class="sig-name descname"><span class="pre">toggle_collection_dynamic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activities</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L285"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.toggle_collection_dynamic" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">toggle_collection_dynamic</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enable</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activities</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L285"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler._KinetoProfile.toggle_collection_dynamic" title="Permalink to this definition">#</a></dt>
 <dd><p>Toggle collection of activities on/off at any point of collection. Currently supports toggling Torch Ops
 (CPU) and CUDA activity supported in Kineto</p>
 <dl class="field-list simple">
@@ -4581,7 +4581,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.profiler.profile">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">profile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activities</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schedule</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">on_trace_ready</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_stack</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_flops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">experimental_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">execution_trace_observer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">acc_events</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_cuda</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_trace_id_callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.profile" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">profile</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">activities</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schedule</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">on_trace_ready</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">record_shapes</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">profile_memory</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_stack</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_flops</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">with_modules</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">experimental_config</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">execution_trace_observer</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">acc_events</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_cuda</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">custom_trace_id_callback</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L551"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.profile" title="Permalink to this definition">#</a></dt>
 <dd><p>Profiler context manager.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4708,13 +4708,13 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 Note: One can also pass any object satisfying the _ITraceObserver interface.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler.profile.get_trace_id">
-<span class="sig-name descname"><span class="pre">get_trace_id</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L856"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.profile.get_trace_id" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_trace_id</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L856"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.profile.get_trace_id" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the current trace ID.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler.profile.set_custom_trace_id_callback">
-<span class="sig-name descname"><span class="pre">set_custom_trace_id_callback</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L850"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.profile.set_custom_trace_id_callback" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_custom_trace_id_callback</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L850"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.profile.set_custom_trace_id_callback" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets a callback to be called when a new trace ID is generated.</p>
 <dl class="field-list simple">
 </dl>
@@ -4722,7 +4722,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.profiler.profile.step">
-<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L828"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.profile.step" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L828"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.profile.step" title="Permalink to this definition">#</a></dt>
 <dd><p>Signals the profiler that the next profiling step has started.</p>
 <dl class="field-list simple">
 </dl>
@@ -4732,7 +4732,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.profiler.ProfilerAction">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">ProfilerAction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.ProfilerAction" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">ProfilerAction</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L446"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.ProfilerAction" title="Permalink to this definition">#</a></dt>
 <dd><p>Profiler actions that can be taken at the specified intervals</p>
 </dd></dl>
 
@@ -4755,7 +4755,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.profiler.schedule">
-<span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wait</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">warmup</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">active</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeat</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_first_wait</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L457"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.schedule" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wait</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">warmup</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">active</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">repeat</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_first</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_first_wait</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L457"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.schedule" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a callable that can be used as profiler <code class="docutils literal notranslate"><span class="pre">schedule</span></code> argument. The profiler will skip
 the first <code class="docutils literal notranslate"><span class="pre">skip_first</span></code> steps, then wait for <code class="docutils literal notranslate"><span class="pre">wait</span></code> steps, then do the warmup for the next <code class="docutils literal notranslate"><span class="pre">warmup</span></code> steps,
 then do the active recording for the next <code class="docutils literal notranslate"><span class="pre">active</span></code> steps and then repeat the cycle starting with <code class="docutils literal notranslate"><span class="pre">wait</span></code> steps.
@@ -4776,7 +4776,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.profiler.tensorboard_trace_handler">
-<span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">tensorboard_trace_handler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dir_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">worker_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_gzip</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/profiler.py#L521"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.tensorboard_trace_handler" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.profiler.</span></span><span class="sig-name descname"><span class="pre">tensorboard_trace_handler</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dir_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">worker_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_gzip</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/profiler.py#L521"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.tensorboard_trace_handler" title="Permalink to this definition">#</a></dt>
 <dd><p>Outputs tracing files to directory of <code class="docutils literal notranslate"><span class="pre">dir_name</span></code>, then that directory can be
 directly delivered to tensorboard as logdir.
 <code class="docutils literal notranslate"><span class="pre">worker_name</span></code> should be unique for each worker in distributed scenario,
@@ -4790,13 +4790,13 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 <h2>Intel Instrumentation and Tracing Technology APIs<a class="headerlink" href="#intel-instrumentation-and-tracing-technology-apis" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.profiler.itt.is_available">
-<span class="sig-prename descclassname"><span class="pre">torch.profiler.itt.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/itt.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.itt.is_available" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.profiler.itt.</span></span><span class="sig-name descname"><span class="pre">is_available</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/itt.py#L31"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.itt.is_available" title="Permalink to this definition">#</a></dt>
 <dd><p>Check if ITT feature is available or not</p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.profiler.itt.mark">
-<span class="sig-prename descclassname"><span class="pre">torch.profiler.itt.</span></span><span class="sig-name descname"><span class="pre">mark</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/itt.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.itt.mark" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.profiler.itt.</span></span><span class="sig-name descname"><span class="pre">mark</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/itt.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.itt.mark" title="Permalink to this definition">#</a></dt>
 <dd><p>Describe an instantaneous event that occurred at some point.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4807,7 +4807,7 @@ <h2>Intel Instrumentation and Tracing Technology APIs<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.profiler.itt.range_push">
-<span class="sig-prename descclassname"><span class="pre">torch.profiler.itt.</span></span><span class="sig-name descname"><span class="pre">range_push</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/itt.py#L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.itt.range_push" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.profiler.itt.</span></span><span class="sig-name descname"><span class="pre">range_push</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">msg</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/itt.py#L38"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.itt.range_push" title="Permalink to this definition">#</a></dt>
 <dd><p>Pushes a range onto a stack of nested range span.  Returns zero-based
 depth of the range that is started.</p>
 <dl class="field-list simple">
@@ -4819,7 +4819,7 @@ <h2>Intel Instrumentation and Tracing Technology APIs<a class="headerlink" href=
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.profiler.itt.range_pop">
-<span class="sig-prename descclassname"><span class="pre">torch.profiler.itt.</span></span><span class="sig-name descname"><span class="pre">range_pop</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/profiler/itt.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.itt.range_pop" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.profiler.itt.</span></span><span class="sig-name descname"><span class="pre">range_pop</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/profiler/itt.py#L49"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.profiler.itt.range_pop" title="Permalink to this definition">#</a></dt>
 <dd><p>Pops a range off of a stack of nested range spans. Returns the
 zero-based depth of the range that is ended.</p>
 </dd></dl>
diff --git a/2.9/quantization.html b/2.9/quantization.html
index d0af97e0c97..72b039cb0c1 100644
--- a/2.9/quantization.html
+++ b/2.9/quantization.html
@@ -4414,17 +4414,17 @@ <h2>Quantization API Reference (Kept since APIs are still public)<a class="heade
 </div>
 <span class="target" id="module-torch.ao"></span><span class="target" id="module-torch.ao.nn"></span><span class="target" id="module-torch.ao.nn.quantizable"></span><span class="target" id="module-torch.ao.nn.quantizable.modules"></span><span class="target" id="module-torch.ao.nn.quantized"></span><span class="target" id="module-torch.ao.nn.quantized.reference"></span><span class="target" id="module-torch.ao.nn.quantized.reference.modules"></span><span class="target" id="module-torch.ao.nn.sparse"></span><span class="target" id="module-torch.ao.nn.sparse.quantized"></span><span class="target" id="module-torch.ao.nn.sparse.quantized.dynamic"></span><span class="target" id="module-torch.ao.ns"></span><span class="target" id="module-torch.ao.ns.fx"></span><span class="target" id="module-torch.ao.quantization.backend_config"></span><span class="target" id="module-torch.ao.pruning"></span><span class="target" id="module-torch.ao.pruning.scheduler"></span><span class="target" id="module-torch.ao.pruning.sparsifier"></span><span class="target" id="module-torch.ao.nn.intrinsic.modules.fused"></span><span class="target" id="module-torch.ao.nn.intrinsic.qat.modules.conv_fused"></span><span class="target" id="module-torch.ao.nn.intrinsic.qat.modules.linear_fused"></span><span class="target" id="module-torch.ao.nn.intrinsic.qat.modules.linear_relu"></span><span class="target" id="module-torch.ao.nn.intrinsic.quantized.dynamic.modules.linear_relu"></span><span class="target" id="module-torch.ao.nn.intrinsic.quantized.modules.bn_relu"></span><span class="target" id="module-torch.ao.nn.intrinsic.quantized.modules.conv_add"></span><span class="target" id="module-torch.ao.nn.intrinsic.quantized.modules.conv_relu"></span><span class="target" id="module-torch.ao.nn.intrinsic.quantized.modules.linear_relu"></span><span class="target" id="module-torch.ao.nn.qat.dynamic.modules.linear"></span><span class="target" id="module-torch.ao.nn.qat.modules.conv"></span><span class="target" id="module-torch.ao.nn.qat.modules.embedding_ops"></span><span class="target" id="module-torch.ao.nn.qat.modules.linear"></span><span class="target" id="module-torch.ao.nn.quantizable.modules.activation"></span><span class="target" id="module-torch.ao.nn.quantizable.modules.rnn"></span><span class="target" id="module-torch.ao.nn.quantized.dynamic.modules.conv"></span><span class="target" id="module-torch.ao.nn.quantized.dynamic.modules.linear"></span><span class="target" id="module-torch.ao.nn.quantized.dynamic.modules.rnn"></span><span class="target" id="module-torch.ao.nn.quantized.modules.activation"></span><span class="target" id="module-torch.ao.nn.quantized.modules.batchnorm"></span><span class="target" id="module-torch.ao.nn.quantized.modules.conv"></span><span class="target" id="module-torch.ao.nn.quantized.modules.dropout"></span><span class="target" id="module-torch.ao.nn.quantized.modules.embedding_ops"></span><span class="target" id="module-torch.ao.nn.quantized.modules.functional_modules"></span><span class="target" id="module-torch.ao.nn.quantized.modules.linear"></span><span class="target" id="module-torch.ao.nn.quantized.modules.normalization"></span><span class="target" id="module-torch.ao.nn.quantized.modules.rnn"></span><span class="target" id="module-torch.ao.nn.quantized.modules.utils"></span><span class="target" id="module-torch.ao.nn.quantized.reference.modules.conv"></span><span class="target" id="module-torch.ao.nn.quantized.reference.modules.linear"></span><span class="target" id="module-torch.ao.nn.quantized.reference.modules.rnn"></span><span class="target" id="module-torch.ao.nn.quantized.reference.modules.sparse"></span><span class="target" id="module-torch.ao.nn.quantized.reference.modules.utils"></span><span class="target" id="module-torch.ao.nn.sparse.quantized.dynamic.linear"></span><span class="target" id="module-torch.ao.nn.sparse.quantized.linear"></span><span class="target" id="module-torch.ao.nn.sparse.quantized.utils"></span><span class="target" id="module-torch.ao.ns.fx.graph_matcher"></span><span class="target" id="module-torch.ao.ns.fx.graph_passes"></span><span class="target" id="module-torch.ao.ns.fx.mappings"></span><span class="target" id="module-torch.ao.ns.fx.n_shadows_utils"></span><span class="target" id="module-torch.ao.ns.fx.ns_types"></span><span class="target" id="module-torch.ao.ns.fx.pattern_utils"></span><span class="target" id="module-torch.ao.ns.fx.qconfig_multi_mapping"></span><span class="target" id="module-torch.ao.ns.fx.weight_utils"></span><span class="target" id="module-torch.ao.ns.fx.utils"></span><span class="target" id="module-torch.ao.pruning.scheduler.base_scheduler"></span><span class="target" id="module-torch.ao.pruning.scheduler.cubic_scheduler"></span><span class="target" id="module-torch.ao.pruning.scheduler.lambda_scheduler"></span><span class="target" id="module-torch.ao.pruning.sparsifier.base_sparsifier"></span><span class="target" id="module-torch.ao.pruning.sparsifier.nearly_diagonal_sparsifier"></span><span class="target" id="module-torch.ao.pruning.sparsifier.utils"></span><span class="target" id="module-torch.ao.pruning.sparsifier.weight_norm_sparsifier"></span><span class="target" id="module-torch.ao.quantization.backend_config.backend_config"></span><span class="target" id="module-torch.ao.quantization.backend_config.executorch"></span><span class="target" id="module-torch.ao.quantization.backend_config.fbgemm"></span><span class="target" id="module-torch.ao.quantization.backend_config.native"></span><span class="target" id="module-torch.ao.quantization.backend_config.onednn"></span><span class="target" id="module-torch.ao.quantization.backend_config.qnnpack"></span><span class="target" id="module-torch.ao.quantization.backend_config.tensorrt"></span><span class="target" id="module-torch.ao.quantization.backend_config.utils"></span><span class="target" id="module-torch.ao.quantization.backend_config.x86"></span><span class="target" id="module-torch.ao.quantization.fake_quantize"></span><span class="target" id="module-torch.ao.quantization.fuser_method_mappings"></span><span class="target" id="module-torch.ao.quantization.fuse_modules"></span><span class="target" id="module-torch.ao.quantization.fx.convert"></span><span class="target" id="module-torch.ao.quantization.fx.custom_config"></span><span class="target" id="module-torch.ao.quantization.fx.fuse"></span><span class="target" id="module-torch.ao.quantization.fx.fuse_handler"></span><span class="target" id="module-torch.ao.quantization.fx.graph_module"></span><span class="target" id="module-torch.ao.quantization.fx.lower_to_fbgemm"></span><span class="target" id="module-torch.ao.quantization.fx.lower_to_qnnpack"></span><span class="target" id="module-torch.ao.quantization.fx.lstm_utils"></span><span class="target" id="module-torch.ao.quantization.fx.match_utils"></span><span class="target" id="module-torch.ao.quantization.fx.pattern_utils"></span><span class="target" id="module-torch.ao.quantization.fx.prepare"></span><span class="target" id="module-torch.ao.quantization.fx.qconfig_mapping_utils"></span><span class="target" id="module-torch.ao.quantization.fx.quantize_handler"></span><span class="target" id="module-torch.ao.quantization.fx.tracer"></span><span class="target" id="module-torch.ao.quantization.fx.utils"></span><span class="target" id="module-torch.ao.quantization.observer"></span><span class="target" id="module-torch.ao.quantization.pt2e.duplicate_dq_pass"></span><span class="target" id="module-torch.ao.quantization.pt2e.export_utils"></span><span class="target" id="module-torch.ao.quantization.pt2e.graph_utils"></span><span class="target" id="module-torch.ao.quantization.pt2e.port_metadata_pass"></span><span class="target" id="module-torch.ao.quantization.pt2e.prepare"></span><span class="target" id="module-torch.ao.quantization.pt2e.qat_utils"></span><span class="target" id="module-torch.ao.quantization.pt2e.representation.rewrite"></span><span class="target" id="module-torch.ao.quantization.pt2e.utils"></span><span class="target" id="module-torch.ao.quantization.pt2e.lowering"></span><span class="target" id="module-torch.ao.quantization.qconfig"></span><span class="target" id="module-torch.ao.quantization.qconfig_mapping"></span><span class="target" id="module-torch.ao.quantization.quant_type"></span><span class="target" id="module-torch.ao.quantization.quantization_mappings"></span><span class="target" id="module-torch.ao.quantization.quantize_fx"></span><span class="target" id="module-torch.ao.quantization.quantize_jit"></span><span class="target" id="module-torch.ao.quantization.quantize_pt2e"></span><span class="target" id="module-torch.ao.quantization.quantizer.composable_quantizer"></span><span class="target" id="module-torch.ao.quantization.quantizer.embedding_quantizer"></span><span class="target" id="module-torch.ao.quantization.quantizer.quantizer"></span><span class="target" id="module-torch.ao.quantization.quantizer.utils"></span><span class="target" id="module-torch.ao.quantization.quantizer.x86_inductor_quantizer"></span><span class="target" id="module-torch.ao.quantization.quantizer.xpu_inductor_quantizer"></span><span class="target" id="module-torch.ao.quantization.quantizer.xnnpack_quantizer"></span><span class="target" id="module-torch.ao.quantization.quantizer.xnnpack_quantizer_utils"></span><span class="target" id="module-torch.ao.quantization.stubs"></span><span class="target" id="module-torch.ao.quantization.utils"></span><span class="target" id="module-torch.nn.intrinsic.modules.fused"></span><span class="target" id="module-torch.nn.intrinsic.qat.modules.conv_fused"></span><span class="target" id="module-torch.nn.intrinsic.qat.modules.linear_fused"></span><span class="target" id="module-torch.nn.intrinsic.qat.modules.linear_relu"></span><span class="target" id="module-torch.nn.intrinsic.quantized.dynamic.modules.linear_relu"></span><span class="target" id="module-torch.nn.intrinsic.quantized.modules.bn_relu"></span><span class="target" id="module-torch.nn.intrinsic.quantized.modules.conv_relu"></span><span class="target" id="module-torch.nn.intrinsic.quantized.modules.linear_relu"></span><span class="target" id="module-torch.nn.qat.dynamic.modules.linear"></span><span class="target" id="module-torch.nn.qat.modules.conv"></span><span class="target" id="module-torch.nn.qat.modules.embedding_ops"></span><span class="target" id="module-torch.nn.qat.modules.linear"></span><span class="target" id="module-torch.nn.quantizable.modules.activation"></span><span class="target" id="module-torch.nn.quantizable.modules.rnn"></span><span class="target" id="module-torch.nn.quantized.dynamic.modules.conv"></span><span class="target" id="module-torch.nn.quantized.dynamic.modules.linear"></span><span class="target" id="module-torch.nn.quantized.dynamic.modules.rnn"></span><span class="target" id="module-torch.nn.quantized.functional"></span><span class="target" id="module-torch.nn.quantized.modules.activation"></span><span class="target" id="module-torch.nn.quantized.modules.batchnorm"></span><span class="target" id="module-torch.nn.quantized.modules.conv"></span><span class="target" id="module-torch.nn.quantized.modules.dropout"></span><span class="target" id="module-torch.nn.quantized.modules.embedding_ops"></span><span class="target" id="module-torch.nn.quantized.modules.functional_modules"></span><span class="target" id="module-torch.nn.quantized.modules.linear"></span><span class="target" id="module-torch.nn.quantized.modules.normalization"></span><span class="target" id="module-torch.nn.quantized.modules.rnn"></span><span class="target" id="module-torch.nn.quantized.modules.utils"></span><span class="target" id="module-torch.quantization.fake_quantize"></span><span class="target" id="module-torch.quantization.fuse_modules"></span><span class="target" id="module-torch.quantization.fuser_method_mappings"></span><span class="target" id="module-torch.quantization.fx.convert"></span><span class="target" id="module-torch.quantization.fx.fuse"></span><span class="target" id="module-torch.quantization.fx.fusion_patterns"></span><span class="target" id="module-torch.quantization.fx.graph_module"></span><span class="target" id="module-torch.quantization.fx.match_utils"></span><span class="target" id="module-torch.quantization.fx.pattern_utils"></span><span class="target" id="module-torch.quantization.fx.prepare"></span><span class="target" id="module-torch.quantization.fx.quantization_patterns"></span><span class="target" id="module-torch.quantization.fx.quantization_types"></span><span class="target" id="module-torch.quantization.fx.utils"></span><span class="target" id="module-torch.quantization.observer"></span><span class="target" id="module-torch.quantization.qconfig"></span><span class="target" id="module-torch.quantization.quant_type"></span><span class="target" id="module-torch.quantization.quantization_mappings"></span><span class="target" id="module-torch.quantization.quantize"></span><span class="target" id="module-torch.quantization.quantize_fx"></span><span class="target" id="module-torch.quantization.quantize_jit"></span><span class="target" id="module-torch.quantization.stubs"></span><span class="target" id="module-torch.quantization.utils"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.ao.ns.fx.utils.compute_sqnr">
-<span class="sig-prename descclassname"><span class="pre">torch.ao.ns.fx.utils.</span></span><span class="sig-name descname"><span class="pre">compute_sqnr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/ns/fx/utils.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.ns.fx.utils.compute_sqnr" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.ao.ns.fx.utils.</span></span><span class="sig-name descname"><span class="pre">compute_sqnr</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/ns/fx/utils.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.ns.fx.utils.compute_sqnr" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.ao.ns.fx.utils.compute_normalized_l2_error">
-<span class="sig-prename descclassname"><span class="pre">torch.ao.ns.fx.utils.</span></span><span class="sig-name descname"><span class="pre">compute_normalized_l2_error</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/ns/fx/utils.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.ns.fx.utils.compute_normalized_l2_error" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.ao.ns.fx.utils.</span></span><span class="sig-name descname"><span class="pre">compute_normalized_l2_error</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/ns/fx/utils.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.ns.fx.utils.compute_normalized_l2_error" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.ao.ns.fx.utils.compute_cosine_similarity">
-<span class="sig-prename descclassname"><span class="pre">torch.ao.ns.fx.utils.</span></span><span class="sig-name descname"><span class="pre">compute_cosine_similarity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/ao/ns/fx/utils.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.ns.fx.utils.compute_cosine_similarity" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.ao.ns.fx.utils.</span></span><span class="sig-name descname"><span class="pre">compute_cosine_similarity</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">x</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">y</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/ao/ns/fx/utils.py#L413"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ao.ns.fx.utils.compute_cosine_similarity" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </div>
diff --git a/2.9/random.html b/2.9/random.html
index a119f1015a4..7b534b4e926 100644
--- a/2.9/random.html
+++ b/2.9/random.html
@@ -4396,7 +4396,7 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: Aug 07, 2019 | Last Updated On: Jun 18, 2025</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.random.fork_rng">
-<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">fork_rng</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_caller</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fork_rng'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_devices_kw</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'devices'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.fork_rng" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">fork_rng</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_caller</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'fork_rng'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_devices_kw</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'devices'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L125"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.fork_rng" title="Permalink to this definition">#</a></dt>
 <dd><p>Forks the RNG, so that when you return, the RNG is reset
 to the state that it was previously in.</p>
 <dl class="field-list simple">
@@ -4422,7 +4422,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.random.get_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.get_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">get_rng_state</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L22"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.get_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the random number generator state as a <cite>torch.ByteTensor</cite>.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
@@ -4438,7 +4438,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.random.initial_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">initial_seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.initial_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">initial_seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L113"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.initial_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the initial seed for generating random numbers as a
 Python <cite>long</cite>.</p>
 <div class="admonition note">
@@ -4454,7 +4454,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.random.manual_seed">
-<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.manual_seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">manual_seed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">seed</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L32"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.manual_seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the seed for generating random numbers on all devices. Returns a
 <cite>torch.Generator</cite> object.</p>
 <dl class="field-list simple">
@@ -4472,7 +4472,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.random.seed">
-<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.seed" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">seed</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L63"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.seed" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the seed for generating random numbers to a non-deterministic
 random number on all devices. Returns a 64 bit number used to seed the RNG.</p>
 <dl class="field-list simple">
@@ -4484,7 +4484,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.random.set_rng_state">
-<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/random.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.set_rng_state" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.random.</span></span><span class="sig-name descname"><span class="pre">set_rng_state</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">new_state</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/random.py#L10"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.random.set_rng_state" title="Permalink to this definition">#</a></dt>
 <dd><p>Sets the random number generator state.</p>
 <div class="admonition note">
 <p class="admonition-title">Note</p>
diff --git a/2.9/rpc.html b/2.9/rpc.html
index d34bb06506d..d583a2669c7 100644
--- a/2.9/rpc.html
+++ b/2.9/rpc.html
@@ -4477,7 +4477,7 @@ <h2>Basics<a class="headerlink" href="#basics" title="Permalink to this heading"
 framework, RRef framework and distributed autograd.</p>
 <span class="target" id="module-torch.distributed.rpc"></span><dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.rpc.init_rpc">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">init_rpc</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rpc_backend_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/__init__.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.init_rpc" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">init_rpc</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rank</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">world_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rpc_backend_options</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/__init__.py#L92"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.init_rpc" title="Permalink to this definition">#</a></dt>
 <dd><p>Initializes RPC primitives such as the local RPC agent
 and distributed autograd, which immediately makes the current
 process ready to send and receive RPCs.</p>
@@ -4520,7 +4520,7 @@ <h2>Basics<a class="headerlink" href="#basics" title="Permalink to this heading"
 and move it to the desired devices on the callee if necessary.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.rpc.rpc_sync">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">rpc_sync</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/api.py#L758"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.rpc_sync" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">rpc_sync</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/api.py#L758"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.rpc_sync" title="Permalink to this definition">#</a></dt>
 <dd><p>Make a blocking RPC call to run function <code class="docutils literal notranslate"><span class="pre">func</span></code> on worker <code class="docutils literal notranslate"><span class="pre">to</span></code>. RPC
 messages are sent and received in parallel to execution of Python code. This
 method is thread-safe.</p>
@@ -4595,7 +4595,7 @@ <h2>Basics<a class="headerlink" href="#basics" title="Permalink to this heading"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.rpc.rpc_async">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">rpc_async</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/api.py#L832"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.rpc_async" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">rpc_async</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/api.py#L832"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.rpc_async" title="Permalink to this definition">#</a></dt>
 <dd><p>Make a non-blocking RPC call to run function <code class="docutils literal notranslate"><span class="pre">func</span></code> on worker <code class="docutils literal notranslate"><span class="pre">to</span></code>. RPC
 messages are sent and received in parallel to execution of Python code. This
 method is thread-safe. This method will immediately return a
@@ -4692,7 +4692,7 @@ <h2>Basics<a class="headerlink" href="#basics" title="Permalink to this heading"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.rpc.remote">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">remote</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/api.py#L546"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.remote" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">remote</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">func</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1.0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/api.py#L546"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.remote" title="Permalink to this definition">#</a></dt>
 <dd><p>Make a remote call to run <code class="docutils literal notranslate"><span class="pre">func</span></code> on worker <code class="docutils literal notranslate"><span class="pre">to</span></code> and return an
 <code class="xref py py-class docutils literal notranslate"><span class="pre">RRef</span></code> to the result value immediately.
 Worker <code class="docutils literal notranslate"><span class="pre">to</span></code> will be the owner of the returned
@@ -4801,7 +4801,7 @@ <h2>Basics<a class="headerlink" href="#basics" title="Permalink to this heading"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.rpc.get_worker_info">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">get_worker_info</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/api.py#L421"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.get_worker_info" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">get_worker_info</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">worker_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/api.py#L421"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.get_worker_info" title="Permalink to this definition">#</a></dt>
 <dd><p>Get <a class="reference internal" href="#torch.distributed.rpc.WorkerInfo" title="torch.distributed.rpc.WorkerInfo"><code class="xref py py-class docutils literal notranslate"><span class="pre">WorkerInfo</span></code></a> of a given worker name.
 Use this <a class="reference internal" href="#torch.distributed.rpc.WorkerInfo" title="torch.distributed.rpc.WorkerInfo"><code class="xref py py-class docutils literal notranslate"><span class="pre">WorkerInfo</span></code></a> to avoid passing an
 expensive string on every invocation.</p>
@@ -4820,7 +4820,7 @@ <h2>Basics<a class="headerlink" href="#basics" title="Permalink to this heading"
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.rpc.shutdown">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">shutdown</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graceful</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/api.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.shutdown" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">shutdown</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">graceful</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/api.py#L320"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.shutdown" title="Permalink to this definition">#</a></dt>
 <dd><p>Perform a shutdown of the RPC agent, and then destroy the RPC agent. This
 stops the local agent from accepting outstanding requests, and shuts
 down the RPC framework by terminating all RPC threads. If <code class="docutils literal notranslate"><span class="pre">graceful=True</span></code>,
@@ -4901,7 +4901,7 @@ <h2>Basics<a class="headerlink" href="#basics" title="Permalink to this heading"
 how a given function should be treated on the callee side.</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.distributed.rpc.functions.async_execution">
-<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.functions.</span></span><span class="sig-name descname"><span class="pre">async_execution</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/functions.py#L5"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.functions.async_execution" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.functions.</span></span><span class="sig-name descname"><span class="pre">async_execution</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">fn</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/functions.py#L5"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.functions.async_execution" title="Permalink to this definition">#</a></dt>
 <dd><p>A decorator for a function indicating that the return value of the function
 is guaranteed to be a <a class="reference internal" href="futures.html#torch.futures.Future" title="torch.futures.Future"><code class="xref py py-class docutils literal notranslate"><span class="pre">Future</span></code></a> object and this
 function can run asynchronously on the RPC callee. More specifically, the
@@ -5142,7 +5142,7 @@ <h4>TensorPipe Backend<a class="headerlink" href="#tensorpipe-backend" title="Pe
 </div>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.rpc.TensorPipeRpcBackendOptions">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">TensorPipeRpcBackendOptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_worker_threads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rpc_timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">60.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'env://'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_maps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_transports</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_channels</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/options.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.TensorPipeRpcBackendOptions" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.rpc.</span></span><span class="sig-name descname"><span class="pre">TensorPipeRpcBackendOptions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_worker_threads</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">16</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rpc_timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">60.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">init_method</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'env://'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_maps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">devices</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_transports</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_channels</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/options.py#L51"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.TensorPipeRpcBackendOptions" title="Permalink to this definition">#</a></dt>
 <dd><p>The backend options for
 <code class="xref py py-class docutils literal notranslate"><span class="pre">TensorPipeAgent</span></code>, derived from
 <a class="reference internal" href="#torch.distributed.rpc.RpcBackendOptions" title="torch.distributed.rpc.RpcBackendOptions"><code class="xref py py-class docutils literal notranslate"><span class="pre">RpcBackendOptions</span></code></a>.</p>
@@ -5214,7 +5214,7 @@ <h4>TensorPipe Backend<a class="headerlink" href="#tensorpipe-backend" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.rpc.TensorPipeRpcBackendOptions.set_device_map">
-<span class="sig-name descname"><span class="pre">set_device_map</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_map</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/options.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.TensorPipeRpcBackendOptions.set_device_map" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_device_map</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">to</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_map</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/options.py#L112"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.TensorPipeRpcBackendOptions.set_device_map" title="Permalink to this definition">#</a></dt>
 <dd><p>Set device mapping between each RPC caller and callee pair. This
 function can be called multiple times to incrementally add
 device placement configurations.</p>
@@ -5265,7 +5265,7 @@ <h4>TensorPipe Backend<a class="headerlink" href="#tensorpipe-backend" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.rpc.TensorPipeRpcBackendOptions.set_devices">
-<span class="sig-name descname"><span class="pre">set_devices</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">devices</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/rpc/options.py#L170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.TensorPipeRpcBackendOptions.set_devices" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">set_devices</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">devices</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/rpc/options.py#L170"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.rpc.TensorPipeRpcBackendOptions.set_devices" title="Permalink to this definition">#</a></dt>
 <dd><p>Set local devices used by the TensorPipe RPC agent. When processing
 CUDA RPC requests, the TensorPipe RPC agent will properly synchronize
 CUDA streams for all devices in this <code class="docutils literal notranslate"><span class="pre">List</span></code>.</p>
@@ -5612,7 +5612,7 @@ <h4>TensorPipe Backend<a class="headerlink" href="#tensorpipe-backend" title="Pe
 asynchronously if needed via additional APIs supported by RemoteModule.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.nn.api.remote_module.RemoteModule">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.nn.api.remote_module.</span></span><span class="sig-name descname"><span class="pre">RemoteModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/nn/api/remote_module.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.nn.api.remote_module.RemoteModule" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.nn.api.remote_module.</span></span><span class="sig-name descname"><span class="pre">RemoteModule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/nn/api/remote_module.py#L597"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.nn.api.remote_module.RemoteModule" title="Permalink to this definition">#</a></dt>
 <dd><blockquote>
 <div><p>A RemoteModule instance can only be created after RPC initialization.</p>
 <p>It creates a user-specified module on a specified remote node.
@@ -5693,7 +5693,7 @@ <h4>TensorPipe Backend<a class="headerlink" href="#tensorpipe-backend" title="Pe
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.nn.api.remote_module.RemoteModule.get_module_rref">
-<span class="sig-name descname"><span class="pre">get_module_rref</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/nn/api/remote_module.py#L296"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.nn.api.remote_module.RemoteModule.get_module_rref" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_module_rref</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/nn/api/remote_module.py#L296"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.nn.api.remote_module.RemoteModule.get_module_rref" title="Permalink to this definition">#</a></dt>
 <dd><p>Return an <code class="xref py py-class docutils literal notranslate"><span class="pre">RRef</span></code> (<code class="docutils literal notranslate"><span class="pre">RRef[nn.Module]</span></code>) pointing to the remote module.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -5704,7 +5704,7 @@ <h4>TensorPipe Backend<a class="headerlink" href="#tensorpipe-backend" title="Pe
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.distributed.nn.api.remote_module.RemoteModule.remote_parameters">
-<span class="sig-name descname"><span class="pre">remote_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/nn/api/remote_module.py#L277"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.nn.api.remote_module.RemoteModule.remote_parameters" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">remote_parameters</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">recurse</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/nn/api/remote_module.py#L277"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.nn.api.remote_module.RemoteModule.remote_parameters" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a list of <code class="xref py py-class docutils literal notranslate"><span class="pre">RRef</span></code> pointing to the remote module’s parameters.</p>
 <p>This can typically be used in conjunction
 with <a class="reference internal" href="distributed.optim.html#torch.distributed.optim.DistributedOptimizer" title="torch.distributed.optim.DistributedOptimizer"><code class="xref py py-class docutils literal notranslate"><span class="pre">DistributedOptimizer</span></code></a>.</p>
@@ -5785,7 +5785,7 @@ <h2>Distributed Autograd Framework<a class="headerlink" href="#distributed-autog
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.distributed.autograd.context">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.autograd.</span></span><span class="sig-name descname"><span class="pre">context</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/distributed/autograd/__init__.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.autograd.context" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.distributed.autograd.</span></span><span class="sig-name descname"><span class="pre">context</span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/distributed/autograd/__init__.py#L37"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.distributed.autograd.context" title="Permalink to this definition">#</a></dt>
 <dd><p>Context object to wrap forward and backward passes when using
 distributed autograd. The <code class="docutils literal notranslate"><span class="pre">context_id</span></code> generated in the <code class="docutils literal notranslate"><span class="pre">with</span></code>
 statement  is required to uniquely identify a distributed backward pass
diff --git a/2.9/storage.html b/2.9/storage.html
index 1637202861f..49d6db6a08d 100644
--- a/2.9/storage.html
+++ b/2.9/storage.html
@@ -4504,52 +4504,52 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 expect many use cases to require operating at the Storage level!</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.UntypedStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">UntypedStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L466"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">UntypedStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L466"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.bfloat16">
-<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L329"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.bfloat16" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L329"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.bfloat16" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to bfloat16 type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.bool">
-<span class="sig-name descname"><span class="pre">bool</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L325"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.bool" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bool</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L325"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.bool" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to bool type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.byte">
-<span class="sig-name descname"><span class="pre">byte</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.byte" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">byte</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.byte" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to byte type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.byteswap">
-<span class="sig-name descname"><span class="pre">byteswap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L421"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.byteswap" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">byteswap</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L421"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.byteswap" title="Permalink to this definition">#</a></dt>
 <dd><p>Swap bytes in underlying data.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.char">
-<span class="sig-name descname"><span class="pre">char</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.char" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">char</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.char" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to char type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.clone">
-<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L255"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.clone" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L255"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.clone" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a copy of this storage.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.complex_double">
-<span class="sig-name descname"><span class="pre">complex_double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L333"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.complex_double" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">complex_double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L333"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.complex_double" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to complex double type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.complex_float">
-<span class="sig-name descname"><span class="pre">complex_float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L337"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.complex_float" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">complex_float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L337"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.complex_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to complex float type.</p>
 </dd></dl>
 
@@ -4560,13 +4560,13 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.cpu">
-<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L263"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.cpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L263"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.cpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a CPU copy of this storage if it’s not already on the CPU.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.cuda">
-<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.cuda" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L82"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.cuda" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a copy of this object in CUDA memory.</p>
 <p>If this object is already in CUDA memory and on the correct device, then
 no copy is performed and the original object is returned.</p>
@@ -4597,7 +4597,7 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.double">
-<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L293"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.double" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L293"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.double" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to double type.</p>
 </dd></dl>
 
@@ -4621,31 +4621,31 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.float">
-<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L297"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L297"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.float8_e4m3fn">
-<span class="sig-name descname"><span class="pre">float8_e4m3fn</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float8_e4m3fn" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float8_e4m3fn</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L345"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float8_e4m3fn" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float8_e4m3fn type</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.float8_e4m3fnuz">
-<span class="sig-name descname"><span class="pre">float8_e4m3fnuz</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float8_e4m3fnuz" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float8_e4m3fnuz</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L353"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float8_e4m3fnuz" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float8_e4m3fnuz type</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.float8_e5m2">
-<span class="sig-name descname"><span class="pre">float8_e5m2</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L341"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float8_e5m2" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float8_e5m2</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L341"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float8_e5m2" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float8_e5m2 type</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.float8_e5m2fnuz">
-<span class="sig-name descname"><span class="pre">float8_e5m2fnuz</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float8_e5m2fnuz" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float8_e5m2fnuz</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L349"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.float8_e5m2fnuz" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float8_e5m2fnuz type</p>
 </dd></dl>
 
@@ -4679,7 +4679,7 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.get_device">
-<span class="sig-name descname"><span class="pre">get_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.get_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.get_device" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)">int</a></p>
@@ -4689,13 +4689,13 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.half">
-<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L301"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.half" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L301"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.half" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to half type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.hpu">
-<span class="sig-name descname"><span class="pre">hpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.hpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">hpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.hpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a copy of this object in HPU memory.</p>
 <p>If this object is already in HPU memory and on the correct device, then
 no copy is performed and the original object is returned.</p>
@@ -4716,7 +4716,7 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.int">
-<span class="sig-name descname"><span class="pre">int</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.int" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">int</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L309"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.int" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to int type.</p>
 </dd></dl>
 
@@ -4732,7 +4732,7 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.is_pinned">
-<span class="sig-name descname"><span class="pre">is_pinned</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L357"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.is_pinned" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_pinned</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L357"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.is_pinned" title="Permalink to this definition">#</a></dt>
 <dd><p>Determine whether the CPU storage is already pinned on device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4762,13 +4762,13 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.long">
-<span class="sig-name descname"><span class="pre">long</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L305"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.long" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">long</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L305"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.long" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to long type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.mps">
-<span class="sig-name descname"><span class="pre">mps</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L269"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.mps" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">mps</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L269"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.mps" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a MPS copy of this storage if it’s not already on the MPS.</p>
 </dd></dl>
 
@@ -4784,7 +4784,7 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.pin_memory">
-<span class="sig-name descname"><span class="pre">pin_memory</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.pin_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pin_memory</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L373"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.pin_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy the CPU storage to pinned memory, if it’s not already pinned.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4809,7 +4809,7 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.share_memory_">
-<span class="sig-name descname"><span class="pre">share_memory_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L489"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.share_memory_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">share_memory_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L489"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.share_memory_" title="Permalink to this definition">#</a></dt>
 <dd><p>Moves the storage to shared memory.</p>
 <p>This is a no-op for storages already in shared memory and for CUDA
 storages, which do not need to be moved for sharing across processes.
@@ -4844,13 +4844,13 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.short">
-<span class="sig-name descname"><span class="pre">short</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.short" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">short</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L313"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.short" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to short type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.size">
-<span class="sig-name descname"><span class="pre">size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.size" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L74"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.size" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)">int</a></p>
@@ -4860,20 +4860,20 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.to">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L288"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.to" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L288"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.to" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.tolist">
-<span class="sig-name descname"><span class="pre">tolist</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.tolist" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">tolist</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L259"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.tolist" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a list containing the elements of this storage.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.type">
-<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.type" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L77"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.type" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Union" title="(in Python v3.14)"><em>Union</em></a>[<em>_StorageBase</em>, <a class="reference internal" href="#torch.TypedStorage" title="torch.storage.TypedStorage"><em>TypedStorage</em></a>]</p>
@@ -4883,7 +4883,7 @@ <h2>Special cases<a class="headerlink" href="#special-cases" title="Permalink to
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.UntypedStorage.untyped">
-<span class="sig-name descname"><span class="pre">untyped</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L418"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.untyped" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">untyped</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L418"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.UntypedStorage.untyped" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </dd></dl>
@@ -4918,67 +4918,67 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 which stores all of the data that the <a class="reference internal" href="tensors.html#torch.Tensor" title="torch.Tensor"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.Tensor</span></code></a> views.</p>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.TypedStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">TypedStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L671"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">TypedStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L671"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.bfloat16">
-<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1367"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.bfloat16" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bfloat16</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1367"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.bfloat16" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to bfloat16 type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.bool">
-<span class="sig-name descname"><span class="pre">bool</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.bool" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">bool</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1362"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.bool" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to bool type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.byte">
-<span class="sig-name descname"><span class="pre">byte</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1357"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.byte" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">byte</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1357"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.byte" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to byte type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.char">
-<span class="sig-name descname"><span class="pre">char</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1352"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.char" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">char</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1352"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.char" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to char type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.clone">
-<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1145"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.clone" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">clone</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1145"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.clone" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a copy of this storage.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.complex_double">
-<span class="sig-name descname"><span class="pre">complex_double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1372"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.complex_double" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">complex_double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1372"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.complex_double" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to complex double type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.complex_float">
-<span class="sig-name descname"><span class="pre">complex_float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.complex_float" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">complex_float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1377"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.complex_float" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to complex float type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.copy_">
-<span class="sig-name descname"><span class="pre">copy_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1021"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.copy_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">copy_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1021"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.copy_" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.cpu">
-<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.cpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cpu</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1155"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.cpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a CPU copy of this storage if it’s not already on the CPU.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.cuda">
-<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1054"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.cuda" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">cuda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1054"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.cuda" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a copy of this object in CUDA memory.</p>
 <p>If this object is already in CUDA memory and on the correct device, then
 no copy is performed and the original object is returned.</p>
@@ -4999,7 +4999,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.data_ptr">
-<span class="sig-name descname"><span class="pre">data_ptr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.data_ptr" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">data_ptr</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1245"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.data_ptr" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5009,7 +5009,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.double">
-<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1322"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.double" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">double</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1322"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.double" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to double type.</p>
 </dd></dl>
 
@@ -5020,7 +5020,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.element_size">
-<span class="sig-name descname"><span class="pre">element_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1097"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.element_size" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">element_size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1097"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.element_size" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py property">
@@ -5032,47 +5032,47 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.fill_">
-<span class="sig-name descname"><span class="pre">fill_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L688"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.fill_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">fill_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L688"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.fill_" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.float">
-<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.float8_e4m3fn">
-<span class="sig-name descname"><span class="pre">float8_e4m3fn</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1387"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float8_e4m3fn" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float8_e4m3fn</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1387"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float8_e4m3fn" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float8_e4m3fn type</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.float8_e4m3fnuz">
-<span class="sig-name descname"><span class="pre">float8_e4m3fnuz</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float8_e4m3fnuz" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float8_e4m3fnuz</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1397"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float8_e4m3fnuz" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float8_e4m3fnuz type</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.float8_e5m2">
-<span class="sig-name descname"><span class="pre">float8_e5m2</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1382"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float8_e5m2" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float8_e5m2</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1382"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float8_e5m2" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float8_e5m2 type</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.float8_e5m2fnuz">
-<span class="sig-name descname"><span class="pre">float8_e5m2fnuz</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1392"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float8_e5m2fnuz" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">float8_e5m2fnuz</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1392"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.float8_e5m2fnuz" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to float8_e5m2fnuz type</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.from_buffer">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.from_buffer" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_buffer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.from_buffer" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.from_file">
-<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shared</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Storage</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1402"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.from_file" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">from_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shared</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Storage</span></span></span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1402"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.from_file" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a CPU storage backed by a memory-mapped file.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">shared</span></code> is <code class="docutils literal notranslate"><span class="pre">True</span></code>, then memory is shared between all processes.
 All changes are written to the file. If <code class="docutils literal notranslate"><span class="pre">shared</span></code> is <code class="docutils literal notranslate"><span class="pre">False</span></code>, then the changes on
@@ -5095,7 +5095,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.get_device">
-<span class="sig-name descname"><span class="pre">get_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.get_device" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">get_device</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1105"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.get_device" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
 <dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.14)">int</a></p>
@@ -5105,13 +5105,13 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.half">
-<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.half" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">half</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1332"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.half" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to half type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.hpu">
-<span class="sig-name descname"><span class="pre">hpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.hpu" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">hpu</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1067"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.hpu" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a copy of this object in HPU memory.</p>
 <p>If this object is already in HPU memory and on the correct device, then
 no copy is performed and the original object is returned.</p>
@@ -5132,7 +5132,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.int">
-<span class="sig-name descname"><span class="pre">int</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.int" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">int</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.int" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to int type.</p>
 </dd></dl>
 
@@ -5148,7 +5148,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.is_pinned">
-<span class="sig-name descname"><span class="pre">is_pinned</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1160"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.is_pinned" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_pinned</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1160"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.is_pinned" title="Permalink to this definition">#</a></dt>
 <dd><p>Determine whether the CPU TypedStorage is already pinned on device.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5163,7 +5163,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.is_shared">
-<span class="sig-name descname"><span class="pre">is_shared</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1447"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.is_shared" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_shared</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1447"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.is_shared" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py attribute">
@@ -5173,23 +5173,23 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.long">
-<span class="sig-name descname"><span class="pre">long</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1337"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.long" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">long</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1337"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.long" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to long type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.nbytes">
-<span class="sig-name descname"><span class="pre">nbytes</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1029"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.nbytes" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">nbytes</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1029"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.nbytes" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.pickle_storage_type">
-<span class="sig-name descname"><span class="pre">pickle_storage_type</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1229"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.pickle_storage_type" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pickle_storage_type</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1229"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.pickle_storage_type" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.pin_memory">
-<span class="sig-name descname"><span class="pre">pin_memory</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.pin_memory" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">pin_memory</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'cuda'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1173"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.pin_memory" title="Permalink to this definition">#</a></dt>
 <dd><p>Copy the CPU TypedStorage to pinned memory, if it’s not already pinned.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5204,34 +5204,34 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.resizable">
-<span class="sig-name descname"><span class="pre">resizable</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1253"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.resizable" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">resizable</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1253"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.resizable" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.resize_">
-<span class="sig-name descname"><span class="pre">resize_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.resize_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">resize_</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">size</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1257"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.resize_" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.share_memory_">
-<span class="sig-name descname"><span class="pre">share_memory_</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.share_memory_" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">share_memory_</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.share_memory_" title="Permalink to this definition">#</a></dt>
 <dd><p>See <a class="reference internal" href="#torch.UntypedStorage.share_memory_" title="torch.UntypedStorage.share_memory_"><code class="xref py py-meth docutils literal notranslate"><span class="pre">torch.UntypedStorage.share_memory_()</span></code></a></p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.short">
-<span class="sig-name descname"><span class="pre">short</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1347"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.short" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">short</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1347"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.short" title="Permalink to this definition">#</a></dt>
 <dd><p>Casts this storage to short type.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.size">
-<span class="sig-name descname"><span class="pre">size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1219"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.size" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">size</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1219"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.size" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.to">
-<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1080"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.to" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">to</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1080"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.to" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns a copy of this object in device memory.</p>
 <p>If this object is already on the correct device, then no copy is performed
 and the original object is returned.</p>
@@ -5252,13 +5252,13 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.tolist">
-<span class="sig-name descname"><span class="pre">tolist</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1150"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.tolist" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">tolist</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1150"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.tolist" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a list containing the elements of this storage.</p>
 </dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.type">
-<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L1037"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.type" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_blocking</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L1037"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.type" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the type if <cite>dtype</cite> is not provided, else casts this object to
 the specified type.</p>
 <p>If this is already of the correct type, no copy is performed and the
@@ -5283,7 +5283,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.TypedStorage.untyped">
-<span class="sig-name descname"><span class="pre">untyped</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/storage.py#L886"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.untyped" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">untyped</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/storage.py#L886"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.TypedStorage.untyped" title="Permalink to this definition">#</a></dt>
 <dd><p>Return the internal <a class="reference internal" href="#torch.UntypedStorage" title="torch.UntypedStorage"><code class="xref py py-class docutils literal notranslate"><span class="pre">torch.UntypedStorage</span></code></a>.</p>
 </dd></dl>
 
@@ -5291,7 +5291,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.DoubleStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">DoubleStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1874"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.DoubleStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">DoubleStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1874"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.DoubleStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5303,7 +5303,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.FloatStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">FloatStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1885"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.FloatStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">FloatStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1885"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.FloatStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5315,7 +5315,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.HalfStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">HalfStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1896"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.HalfStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">HalfStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1896"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.HalfStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5327,7 +5327,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.LongStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">LongStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1907"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.LongStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">LongStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1907"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.LongStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5339,7 +5339,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.IntStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">IntStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1918"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.IntStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">IntStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1918"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.IntStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5351,7 +5351,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ShortStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">ShortStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1929"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ShortStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">ShortStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1929"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ShortStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5363,7 +5363,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.CharStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">CharStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1940"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.CharStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">CharStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1940"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.CharStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5375,7 +5375,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ByteStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">ByteStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1863"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ByteStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">ByteStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1863"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ByteStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5387,7 +5387,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.BoolStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">BoolStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.BoolStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">BoolStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1951"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.BoolStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5399,7 +5399,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.BFloat16Storage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">BFloat16Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1962"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.BFloat16Storage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">BFloat16Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1962"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.BFloat16Storage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5411,7 +5411,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ComplexDoubleStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">ComplexDoubleStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1973"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ComplexDoubleStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">ComplexDoubleStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1973"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ComplexDoubleStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5423,7 +5423,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.ComplexFloatStorage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">ComplexFloatStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1984"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ComplexFloatStorage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">ComplexFloatStorage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1984"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.ComplexFloatStorage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5435,7 +5435,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.QUInt8Storage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QUInt8Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L1995"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QUInt8Storage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QUInt8Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L1995"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QUInt8Storage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5447,7 +5447,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.QInt8Storage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QInt8Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L2006"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QInt8Storage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QInt8Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L2006"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QInt8Storage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5459,7 +5459,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.QInt32Storage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QInt32Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L2017"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QInt32Storage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QInt32Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L2017"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QInt32Storage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5471,7 +5471,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.QUInt4x2Storage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QUInt4x2Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L2028"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QUInt4x2Storage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QUInt4x2Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L2028"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QUInt4x2Storage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
@@ -5483,7 +5483,7 @@ <h2>Legacy Typed Storage<a class="headerlink" href="#legacy-typed-storage" title
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.QUInt2x4Storage">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QUInt2x4Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L2039"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QUInt2x4Storage" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">QUInt2x4Storage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">wrap_storage</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_internal</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L2039"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.QUInt2x4Storage" title="Permalink to this definition">#</a></dt>
 <dd><dl class="field-list simple">
 </dl>
 <dl class="py attribute">
diff --git a/2.9/tensorboard.html b/2.9/tensorboard.html
index 93061b88dcf..8cd78993b56 100644
--- a/2.9/tensorboard.html
+++ b/2.9/tensorboard.html
@@ -4455,7 +4455,7 @@
 </div>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.tensorboard.writer.</span></span><span class="sig-name descname"><span class="pre">SummaryWriter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">comment</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">purge_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_queue</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flush_secs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">120</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filename_suffix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.utils.tensorboard.writer.</span></span><span class="sig-name descname"><span class="pre">SummaryWriter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">comment</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">purge_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_queue</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flush_secs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">120</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filename_suffix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L172"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter" title="Permalink to this definition">#</a></dt>
 <dd><p>Writes entries directly to event files in the log_dir to be consumed by TensorBoard.</p>
 <p>The <cite>SummaryWriter</cite> class provides a high-level API to create an event file
 in a given directory and add summaries and events to it. The class updates the
@@ -4464,7 +4464,7 @@
 training.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.__init__">
-<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">comment</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">purge_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_queue</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flush_secs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">120</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filename_suffix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L182"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.__init__" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">log_dir</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">comment</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">purge_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_queue</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flush_secs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">120</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">filename_suffix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L182"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.__init__" title="Permalink to this definition">#</a></dt>
 <dd><p>Create a <cite>SummaryWriter</cite> that will write out events and summaries to the event file.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4511,7 +4511,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_scalar">
-<span class="sig-name descname"><span class="pre">add_scalar</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scalar_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_style</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">double_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_scalar" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_scalar</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">scalar_value</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_style</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">double_precision</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L342"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_scalar" title="Permalink to this definition">#</a></dt>
 <dd><p>Add scalar data to summary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4541,7 +4541,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_scalars">
-<span class="sig-name descname"><span class="pre">add_scalars</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">main_tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag_scalar_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_scalars" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_scalars</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">main_tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag_scalar_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L383"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_scalars" title="Permalink to this definition">#</a></dt>
 <dd><p>Add many scalar data to summary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4573,7 +4573,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_histogram">
-<span class="sig-name descname"><span class="pre">add_histogram</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">values</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bins</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tensorflow'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_bins</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L459"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_histogram" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_histogram</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">values</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bins</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'tensorflow'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_bins</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L459"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_histogram" title="Permalink to this definition">#</a></dt>
 <dd><p>Add histogram to summary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4604,7 +4604,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_image">
-<span class="sig-name descname"><span class="pre">add_image</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">img_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dataformats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'CHW'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L577"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_image" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_image</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">img_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dataformats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'CHW'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L577"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_image" title="Permalink to this definition">#</a></dt>
 <dd><p>Add image data to summary.</p>
 <p>Note that this requires the <code class="docutils literal notranslate"><span class="pre">pillow</span></code> package.</p>
 <dl class="field-list simple">
@@ -4652,7 +4652,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_images">
-<span class="sig-name descname"><span class="pre">add_images</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">img_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dataformats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'NCHW'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L628"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_images" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_images</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">img_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dataformats</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'NCHW'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L628"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_images" title="Permalink to this definition">#</a></dt>
 <dd><p>Add batched image data to summary.</p>
 <p>Note that this requires the <code class="docutils literal notranslate"><span class="pre">pillow</span></code> package.</p>
 <dl class="field-list simple">
@@ -4693,7 +4693,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_figure">
-<span class="sig-name descname"><span class="pre">add_figure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">figure</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">close</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L723"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_figure" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_figure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">figure</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">close</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L723"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_figure" title="Permalink to this definition">#</a></dt>
 <dd><p>Render matplotlib figure into an image and add it to summary.</p>
 <p>Note that this requires the <code class="docutils literal notranslate"><span class="pre">matplotlib</span></code> package.</p>
 <dl class="field-list simple">
@@ -4712,7 +4712,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_video">
-<span class="sig-name descname"><span class="pre">add_video</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vid_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L761"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_video" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_video</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vid_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fps</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L761"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_video" title="Permalink to this definition">#</a></dt>
 <dd><p>Add video data to summary.</p>
 <p>Note that this requires the <code class="docutils literal notranslate"><span class="pre">moviepy</span></code> package.</p>
 <dl class="field-list simple">
@@ -4735,7 +4735,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_audio">
-<span class="sig-name descname"><span class="pre">add_audio</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">snd_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sample_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">44100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_audio" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_audio</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">snd_tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sample_rate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">44100</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L781"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_audio" title="Permalink to this definition">#</a></dt>
 <dd><p>Add audio data to summary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4757,7 +4757,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_text">
-<span class="sig-name descname"><span class="pre">add_text</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">text_string</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L801"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_text" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_text</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">text_string</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L801"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_text" title="Permalink to this definition">#</a></dt>
 <dd><p>Add text data to summary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4779,7 +4779,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_graph">
-<span class="sig-name descname"><span class="pre">add_graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_to_model</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_strict_trace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L824"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_graph" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_graph</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_to_model</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_strict_trace</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L824"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_graph" title="Permalink to this definition">#</a></dt>
 <dd><p>Add graph data to summary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4798,7 +4798,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_embedding">
-<span class="sig-name descname"><span class="pre">add_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mat</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label_img</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'default'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata_header</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_embedding" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_embedding</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">mat</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">label_img</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">tag</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'default'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metadata_header</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L853"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_embedding" title="Permalink to this definition">#</a></dt>
 <dd><p>Add embedding projector data to summary.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -4847,7 +4847,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_pr_curve">
-<span class="sig-name descname"><span class="pre">add_pr_curve</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">predictions</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_thresholds</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">127</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L958"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_pr_curve" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_pr_curve</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">labels</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">predictions</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_thresholds</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">127</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">weights</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L958"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_pr_curve" title="Permalink to this definition">#</a></dt>
 <dd><p>Add precision recall curve.</p>
 <p>Plotting a precision-recall curve lets you understand your model’s
 performance under different threshold settings. With this function,
@@ -4882,7 +4882,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_custom_scalars">
-<span class="sig-name descname"><span class="pre">add_custom_scalars</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">layout</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L1094"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_custom_scalars" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_custom_scalars</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">layout</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L1094"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_custom_scalars" title="Permalink to this definition">#</a></dt>
 <dd><p>Create special chart by collecting charts tags in ‘scalars’.</p>
 <p>NOTE: This function can only be called once for each SummaryWriter() object.</p>
 <p>Because it only provides metadata to tensorboard, the function can be called before or after the training loop.</p>
@@ -4906,7 +4906,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_mesh">
-<span class="sig-name descname"><span class="pre">add_mesh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vertices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">colors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">faces</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">config_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L1118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_mesh" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_mesh</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vertices</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">colors</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">faces</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">config_dict</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">walltime</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L1118"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_mesh" title="Permalink to this definition">#</a></dt>
 <dd><p>Add meshes or 3D point clouds to TensorBoard.</p>
 <p>The visualization is based on Three.js,
 so it allows users to interact with the rendered object. Besides the basic definitions
@@ -4964,7 +4964,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.add_hparams">
-<span class="sig-name descname"><span class="pre">add_hparams</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hparam_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metric_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hparam_domain_discrete</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_hparams" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">add_hparams</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">hparam_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">metric_dict</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hparam_domain_discrete</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_step</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L287"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.add_hparams" title="Permalink to this definition">#</a></dt>
 <dd><p>Add a set of hyperparameters to be compared in TensorBoard.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
@@ -5000,7 +5000,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.flush">
-<span class="sig-name descname"><span class="pre">flush</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.flush" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">flush</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L1185"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.flush" title="Permalink to this definition">#</a></dt>
 <dd><p>Flushes the event file to disk.</p>
 <p>Call this method to make sure that all pending events have been written to
 disk.</p>
@@ -5008,7 +5008,7 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.utils.tensorboard.writer.SummaryWriter.close">
-<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/utils/tensorboard/writer.py#L1196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.close" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/utils/tensorboard/writer.py#L1196"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.utils.tensorboard.writer.SummaryWriter.close" title="Permalink to this definition">#</a></dt>
 <dd></dd></dl>
 
 </dd></dl>
diff --git a/2.9/testing.html b/2.9/testing.html
index cb9d3ad6b8e..b1a80177d72 100644
--- a/2.9/testing.html
+++ b/2.9/testing.html
@@ -4396,7 +4396,7 @@
 <p class="date-info-last-verified" style="color: #6c6c6d; font-size: small;">Created On: May 07, 2021 | Last Updated On: Jun 10, 2025</p>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.testing.assert_close">
-<span class="sig-prename descclassname"><span class="pre">torch.testing.</span></span><span class="sig-name descname"><span class="pre">assert_close</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">actual</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_subclasses</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">equal_nan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">msg</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/testing/_comparison.py#L1317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.testing.assert_close" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.testing.</span></span><span class="sig-name descname"><span class="pre">assert_close</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">actual</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">allow_subclasses</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">equal_nan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_layout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">check_stride</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">msg</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/testing/_comparison.py#L1317"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.testing.assert_close" title="Permalink to this definition">#</a></dt>
 <dd><p>Asserts that <code class="docutils literal notranslate"><span class="pre">actual</span></code> and <code class="docutils literal notranslate"><span class="pre">expected</span></code> are close.</p>
 <p>If <code class="docutils literal notranslate"><span class="pre">actual</span></code> and <code class="docutils literal notranslate"><span class="pre">expected</span></code> are strided, non-quantized, real-valued, and finite, they are considered close if</p>
 <div class="math">
@@ -4676,7 +4676,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.testing.make_tensor">
-<span class="sig-prename descclassname"><span class="pre">torch.testing.</span></span><span class="sig-name descname"><span class="pre">make_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">low</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">high</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">noncontiguous</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude_zero</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/testing/_creation.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.testing.make_tensor" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.testing.</span></span><span class="sig-name descname"><span class="pre">make_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">shape</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">low</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">high</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">requires_grad</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">noncontiguous</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">exclude_zero</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">memory_format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/testing/_creation.py#L45"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.testing.make_tensor" title="Permalink to this definition">#</a></dt>
 <dd><p>Creates a tensor with the given <code class="xref py py-attr docutils literal notranslate"><span class="pre">shape</span></code>, <code class="xref py py-attr docutils literal notranslate"><span class="pre">device</span></code>, and <code class="xref py py-attr docutils literal notranslate"><span class="pre">dtype</span></code>, and filled with
 values uniformly drawn from <code class="docutils literal notranslate"><span class="pre">[low,</span> <span class="pre">high)</span></code>.</p>
 <p>If <code class="xref py py-attr docutils literal notranslate"><span class="pre">low</span></code> or <code class="xref py py-attr docutils literal notranslate"><span class="pre">high</span></code> are specified and are outside the range of the <code class="xref py py-attr docutils literal notranslate"><span class="pre">dtype</span></code>’s representable
@@ -4777,7 +4777,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.testing.assert_allclose">
-<span class="sig-prename descclassname"><span class="pre">torch.testing.</span></span><span class="sig-name descname"><span class="pre">assert_allclose</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">actual</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">equal_nan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">msg</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/testing/_comparison.py#L1592"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.testing.assert_allclose" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.testing.</span></span><span class="sig-name descname"><span class="pre">assert_allclose</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">actual</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">rtol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">atol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">equal_nan</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">msg</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/testing/_comparison.py#L1592"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.testing.assert_allclose" title="Permalink to this definition">#</a></dt>
 <dd><div class="admonition warning">
 <p class="admonition-title">Warning</p>
 <p><a class="reference internal" href="#torch.testing.assert_allclose" title="torch.testing.assert_allclose"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.testing.assert_allclose()</span></code></a> is deprecated since <code class="docutils literal notranslate"><span class="pre">1.12</span></code> and will be removed in a future release.
diff --git a/2.9/torch.compiler_aot_inductor.html b/2.9/torch.compiler_aot_inductor.html
index 4bdcd44a9d1..7f75b0eac54 100644
--- a/2.9/torch.compiler_aot_inductor.html
+++ b/2.9/torch.compiler_aot_inductor.html
@@ -4595,7 +4595,7 @@ <h2>Troubleshooting<a class="headerlink" href="#troubleshooting" title="Permalin
 <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._inductor.aoti_compile_and_package">
-<span class="sig-prename descclassname"><span class="pre">torch._inductor.</span></span><span class="sig-name descname"><span class="pre">aoti_compile_and_package</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">exported_program</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_deprecated_unused_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_deprecated_unused_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">package_path</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inductor_configs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_inductor/__init__.py#L55"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._inductor.aoti_compile_and_package" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._inductor.</span></span><span class="sig-name descname"><span class="pre">aoti_compile_and_package</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">exported_program</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_deprecated_unused_args</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">_deprecated_unused_kwargs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">package_path</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">inductor_configs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_inductor/__init__.py#L55"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._inductor.aoti_compile_and_package" title="Permalink to this definition">#</a></dt>
 <dd><p>Compiles the exported program with AOTInductor, and packages it into a .pt2
 artifact specified by the input package_path. To load the package, you can
 call <code class="docutils literal notranslate"><span class="pre">torch._inductor.aoti_load_package(package_path)</span></code>.</p>
@@ -4645,7 +4645,7 @@ <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch._inductor.aoti_load_package">
-<span class="sig-prename descclassname"><span class="pre">torch._inductor.</span></span><span class="sig-name descname"><span class="pre">aoti_load_package</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_single_threaded</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/_inductor/__init__.py#L239"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._inductor.aoti_load_package" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch._inductor.</span></span><span class="sig-name descname"><span class="pre">aoti_load_package</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">run_single_threaded</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device_index</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">-1</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/_inductor/__init__.py#L239"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch._inductor.aoti_load_package" title="Permalink to this definition">#</a></dt>
 <dd><p>Loads the model from the PT2 package.</p>
 <p>If multiple models were packaged into the PT2, this will load the default
 model. To load a specific model, you can directly call the load API</p>
diff --git a/2.9/torch.html b/2.9/torch.html
index 014443e8070..4598478ba4b 100644
--- a/2.9/torch.html
+++ b/2.9/torch.html
@@ -6159,13 +6159,13 @@ <h2>Utilities<a class="headerlink" href="#utilities" title="Permalink to this he
 <h2>Symbolic Numbers<a class="headerlink" href="#symbolic-numbers" title="Permalink to this heading">#</a></h2>
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.SymInt">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">SymInt</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L430"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymInt" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">SymInt</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L430"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymInt" title="Permalink to this definition">#</a></dt>
 <dd><p>Like an int (including magic methods), but redirects all operations on the
 wrapped node. This is used in particular to symbolically record operations
 in the symbolic shape workflow.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.SymInt.as_integer_ratio">
-<span class="sig-name descname"><span class="pre">as_integer_ratio</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymInt.as_integer_ratio" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">as_integer_ratio</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L612"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymInt.as_integer_ratio" title="Permalink to this definition">#</a></dt>
 <dd><p>Represent this int as an exact integer ratio</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -6178,13 +6178,13 @@ <h2>Symbolic Numbers<a class="headerlink" href="#symbolic-numbers" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.SymFloat">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">SymFloat</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">SymFloat</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L627"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat" title="Permalink to this definition">#</a></dt>
 <dd><p>Like a float (including magic methods), but redirects all operations on the
 wrapped node. This is used in particular to symbolically record operations
 in the symbolic shape workflow.</p>
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.SymFloat.as_integer_ratio">
-<span class="sig-name descname"><span class="pre">as_integer_ratio</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat.as_integer_ratio" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">as_integer_ratio</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L724"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat.as_integer_ratio" title="Permalink to this definition">#</a></dt>
 <dd><p>Represent this float as an exact integer ratio</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -6195,7 +6195,7 @@ <h2>Symbolic Numbers<a class="headerlink" href="#symbolic-numbers" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.SymFloat.conjugate">
-<span class="sig-name descname"><span class="pre">conjugate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L737"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat.conjugate" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">conjugate</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L737"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat.conjugate" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the complex conjugate of the float.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -6206,7 +6206,7 @@ <h2>Symbolic Numbers<a class="headerlink" href="#symbolic-numbers" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.SymFloat.hex">
-<span class="sig-name descname"><span class="pre">hex</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L741"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat.hex" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">hex</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L741"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat.hex" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns the hexadecimal representation of the float.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Return type</dt>
@@ -6217,7 +6217,7 @@ <h2>Symbolic Numbers<a class="headerlink" href="#symbolic-numbers" title="Permal
 
 <dl class="py method">
 <dt class="sig sig-object py" id="torch.SymFloat.is_integer">
-<span class="sig-name descname"><span class="pre">is_integer</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L720"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat.is_integer" title="Permalink to this definition">#</a></dt>
+<span class="sig-name descname"><span class="pre">is_integer</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L720"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymFloat.is_integer" title="Permalink to this definition">#</a></dt>
 <dd><p>Return True if the float is an integer.</p>
 </dd></dl>
 
@@ -6225,7 +6225,7 @@ <h2>Symbolic Numbers<a class="headerlink" href="#symbolic-numbers" title="Permal
 
 <dl class="py class">
 <dt class="sig sig-object py" id="torch.SymBool">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">SymBool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/__init__.py#L746"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymBool" title="Permalink to this definition">#</a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">torch.</span></span><span class="sig-name descname"><span class="pre">SymBool</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">node</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/__init__.py#L746"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.SymBool" title="Permalink to this definition">#</a></dt>
 <dd><p>Like a bool (including magic methods), but redirects all operations on the
 wrapped node. This is used in particular to symbolically record operations
 in the symbolic shape workflow.</p>
diff --git a/2.9/torch.overrides.html b/2.9/torch.overrides.html
index c2f3fb8aec1..bc69099e1e1 100644
--- a/2.9/torch.overrides.html
+++ b/2.9/torch.overrides.html
@@ -4401,7 +4401,7 @@
 <h2>Functions<a class="headerlink" href="#functions" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.overrides.get_ignored_functions">
-<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">get_ignored_functions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/overrides.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.get_ignored_functions" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">get_ignored_functions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/overrides.py#L101"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.get_ignored_functions" title="Permalink to this definition">#</a></dt>
 <dd><p>Return public functions that cannot be overridden by <code class="docutils literal notranslate"><span class="pre">__torch_function__</span></code>.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4424,7 +4424,7 @@ <h2>Functions<a class="headerlink" href="#functions" title="Permalink to this he
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.overrides.get_overridable_functions">
-<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">get_overridable_functions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/overrides.py#L1901"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.get_overridable_functions" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">get_overridable_functions</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/overrides.py#L1901"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.get_overridable_functions" title="Permalink to this definition">#</a></dt>
 <dd><p>List functions that are overridable via __torch_function__</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4439,7 +4439,7 @@ <h2>Functions<a class="headerlink" href="#functions" title="Permalink to this he
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.overrides.resolve_name">
-<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">resolve_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/overrides.py#L1914"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.resolve_name" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">resolve_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">f</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/overrides.py#L1914"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.resolve_name" title="Permalink to this definition">#</a></dt>
 <dd><p>Get a human readable string name for a function passed to
 __torch_function__</p>
 <dl class="field-list simple">
@@ -4458,7 +4458,7 @@ <h2>Functions<a class="headerlink" href="#functions" title="Permalink to this he
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.overrides.get_testing_overrides">
-<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">get_testing_overrides</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/overrides.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.get_testing_overrides" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">get_testing_overrides</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/overrides.py#L408"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.get_testing_overrides" title="Permalink to this definition">#</a></dt>
 <dd><p>Return a dict containing dummy overrides for all overridable functions</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
@@ -4482,7 +4482,7 @@ <h2>Functions<a class="headerlink" href="#functions" title="Permalink to this he
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.overrides.handle_torch_function">
-<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">handle_torch_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">public_api</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relevant_args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/overrides.py#L1677"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.handle_torch_function" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">handle_torch_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">public_api</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">relevant_args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/overrides.py#L1677"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.handle_torch_function" title="Permalink to this definition">#</a></dt>
 <dd><p>Implement a function with checks for <code class="docutils literal notranslate"><span class="pre">__torch_function__</span></code> overrides.</p>
 <p>See torch::autograd::handle_torch_function for the equivalent of this
 function in the C++ implementation.</p>
@@ -4545,7 +4545,7 @@ <h2>Functions<a class="headerlink" href="#functions" title="Permalink to this he
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.overrides.is_tensor_like">
-<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">is_tensor_like</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inp</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/overrides.py#L1969"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.is_tensor_like" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">is_tensor_like</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">inp</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/overrides.py#L1969"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.is_tensor_like" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns <code class="docutils literal notranslate"><span class="pre">True</span></code> if the passed-in input is a Tensor-like.</p>
 <p>Currently, this occurs whenever there’s a <code class="docutils literal notranslate"><span class="pre">__torch_function__</span></code>
 attribute on the type of the input.</p>
@@ -4579,7 +4579,7 @@ <h2>Functions<a class="headerlink" href="#functions" title="Permalink to this he
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.overrides.is_tensor_method_or_property">
-<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">is_tensor_method_or_property</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/overrides.py#L1943"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.is_tensor_method_or_property" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">is_tensor_method_or_property</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/overrides.py#L1943"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.is_tensor_method_or_property" title="Permalink to this definition">#</a></dt>
 <dd><p>Returns True if the function passed in is a handler for a
 method or property belonging to <code class="docutils literal notranslate"><span class="pre">torch.Tensor</span></code>, as passed
 into <code class="docutils literal notranslate"><span class="pre">__torch_function__</span></code>.</p>
@@ -4609,7 +4609,7 @@ <h2>Functions<a class="headerlink" href="#functions" title="Permalink to this he
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.overrides.wrap_torch_function">
-<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">wrap_torch_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dispatcher</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/overrides.py#L1561"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.wrap_torch_function" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.overrides.</span></span><span class="sig-name descname"><span class="pre">wrap_torch_function</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">dispatcher</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/overrides.py#L1561"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.overrides.wrap_torch_function" title="Permalink to this definition">#</a></dt>
 <dd><p>Wraps a given function with <code class="docutils literal notranslate"><span class="pre">__torch_function__</span></code> -related functionality.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
diff --git a/2.9/torch_cuda_memory.html b/2.9/torch_cuda_memory.html
index cc5b745fa4f..32dc1c79efe 100644
--- a/2.9/torch_cuda_memory.html
+++ b/2.9/torch_cuda_memory.html
@@ -4458,7 +4458,7 @@ <h2>Allocator State History<a class="headerlink" href="#allocator-state-history"
 <h2>Snapshot API Reference<a class="headerlink" href="#snapshot-api-reference" title="Permalink to this heading">#</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory._record_memory_history">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">_record_memory_history</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stacks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_entries</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">9223372036854775807</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">clear_history</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compile_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_record_annotations</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L864"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory._record_memory_history" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">_record_memory_history</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stacks</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'all'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_entries</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">9223372036854775807</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">clear_history</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compile_context</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">global_record_annotations</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L864"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory._record_memory_history" title="Permalink to this definition">#</a></dt>
 <dd><p>Enable recording of stack traces associated with memory
 allocations, so you can tell what allocated any piece of memory in
 <a class="reference internal" href="#torch.cuda.memory._snapshot" title="torch.cuda.memory._snapshot"><code class="xref py py-func docutils literal notranslate"><span class="pre">torch.cuda.memory._snapshot()</span></code></a>.</p>
@@ -4539,7 +4539,7 @@ <h3>Latency impact<a class="headerlink" href="#latency-impact" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory._snapshot">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">_snapshot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory._snapshot" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">_snapshot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L963"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory._snapshot" title="Permalink to this definition">#</a></dt>
 <dd><p>Save a snapshot of CUDA memory state at the time it was called.</p>
 <p>The state is represented as a dictionary with the following structure.</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">Snapshot</span><span class="p">(</span><span class="n">TypedDict</span><span class="p">):</span>
@@ -4622,7 +4622,7 @@ <h3>Latency impact<a class="headerlink" href="#latency-impact" title="Permalink
 
 <dl class="py function">
 <dt class="sig sig-object py" id="torch.cuda.memory._dump_snapshot">
-<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">_dump_snapshot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'dump_snapshot.pickle'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.1/torch/cuda/memory.py#L1046"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory._dump_snapshot" title="Permalink to this definition">#</a></dt>
+<span class="sig-prename descclassname"><span class="pre">torch.cuda.memory.</span></span><span class="sig-name descname"><span class="pre">_dump_snapshot</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'dump_snapshot.pickle'</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/pytorch/pytorch/blob/v2.9.0/torch/cuda/memory.py#L1046"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#torch.cuda.memory._dump_snapshot" title="Permalink to this definition">#</a></dt>
 <dd><p>Save a pickled version of the <cite>torch.memory._snapshot()</cite> dictionary to a file.</p>
 <p>This file can be opened by the interactive snapshot viewer at pytorch.org/memory_viz</p>
 <p>Snapshot file sizes scale with <cite>max_entries</cite> and stack trace depth per entry,
diff --git a/replace_github_links.sh b/replace_github_links.sh
index 7ca5e217f84..126fc2edc29 100755
--- a/replace_github_links.sh
+++ b/replace_github_links.sh
@@ -1,18 +1,17 @@
 #!/bin/bash
-# Replaces GitHub links from v2.7.1 to v2.7.0 in all html files in a directory
+# Replaces GitHub links from v2.9.1 to v2.9.0 in all html files in a directory
 #
 # Usage:
 # ./replace_github_links.sh directory
 #
 # Example (from the root directory)
-# ./replace_github_links.sh 2.7
+# ./replace_github_links.sh 2.9
 
 if [ "$1" == "" ]; then
   echo "Incorrect usage. Correct Usage: replace_github_links.sh <directory>"
   exit 1
 fi
 
-find $1 -name "*.html" -print0 | xargs -0 sed -i 's|github.com/pytorch/pytorch/blob/v2.7.1|github.com/pytorch/pytorch/blob/v2.7.0|g'
-
-echo "Replaced v2.7.1 with v2.7.0 in GitHub links in $1 directory"
+find $1 -name "*.html" -print0 | xargs -0 sed -i 's|github.com/pytorch/pytorch/blob/v2.9.1|github.com/pytorch/pytorch/blob/v2.9.0|g'
 
+echo "Replaced v2.9.1 with v2.9.0 in GitHub links in $1 directory"